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

    Neuronpedia

    INDEX
    Explanations

    negations and conditional statements regarding necessity and meaning

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

    not necessarily mean

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.92
     AssemblyTitle
    -0.74
    endpush
    -0.66
     HasFactory
    -0.66
    tagHelperRunner
    -0.65
    SharedCtor
    -0.65
    RenderAtEndOf
    -0.65
     Normdatei
    -0.65
    IntoConstraints
    -0.62
    ConstraintMaker
    -0.61
    POSITIVE LOGITS
    不一定
    0.51
    未必
    0.47
     necessarily
    0.42
     nemus
    0.40
     необ
    0.38
    并不
    0.36
     Stich
    0.36
     schließt
    0.35
     бывают
    0.34
    不見
    0.34
    Act Density 0.380%

    No Known Activations