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

    Neuronpedia

    INDEX
    Explanations

    Java programming language components and interfaces

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

    mathematical and scientific notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Espèce
    -0.63
    argout
    -0.60
    agonia
    -0.60
     Infórmanos
    -0.56
    transQ
    -0.55
    heets
    -0.54
    olverine
    -0.53
    bale
    -0.52
    thora
    -0.51
    bray
    -0.51
    POSITIVE LOGITS
    }}}
    0.34
     titulado
    0.33
    sometimes
    0.33
    DebuggerStep
    0.32
    cepción
    0.32
     resourceCulture
    0.32
     lær
    0.31
     docteur
    0.31
    Prezzo
    0.31
     "'");
    0.31
    Act Density 0.001%

    No Known Activations