Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and instructions regarding user interactions or documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    preceding question marks

    np_acts-logits-general · gemini-2.0-flash

    qualifiers and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     put
    -0.70
    ,
    -0.60
    .
    -0.55
     no
    -0.54
     and
    -0.54
     on
    -0.52
     for
    -0.52
    -
    -0.52
     in
    -0.52
     
    -0.51
    POSITIVE LOGITS
     Roskov
    1.54
    Geplaatst
    1.46
     otomatig
    1.31
     autorytatywna
    1.30
    Tikang
    1.29
     AssemblyProduct
    1.25
     beginnetje
    1.23
    LookAnd
    1.23
    InjectAttribute
    1.18
    IntoConstraints
    1.16
    Act Density 0.261%

    No Known Activations