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

    Neuronpedia

    INDEX
    Explanations

    ance suffix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    heel
    -0.06
     objects
    -0.06
     initComponents
    -0.06
    765
    -0.06
    ablytyped
    -0.06
    .savefig
    -0.06
    Browser
    -0.06
     appalling
    -0.06
     beet
    -0.06
    hetto
    -0.06
    POSITIVE LOGITS
     guidance
    0.14
     Guidance
    0.12
     Vance
    0.08
    GUID
    0.08
     regulation
    0.08
     supervision
    0.08
    υγ
    0.08
    Movement
    0.07
    _GU
    0.07
    dration
    0.07
    Act Density 0.007%

    No Known Activations