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

    Neuronpedia

    INDEX
    Explanations

    provide

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Expr
    -0.07
    Op
    -0.07
     newest
    -0.07
     iP
    -0.06
    USA
    -0.06
     linguistic
    -0.06
     bác
    -0.06
     νεφ
    -0.06
     XC
    -0.06
     Builds
    -0.06
    POSITIVE LOGITS
            	↵
    0.07
     deprivation
    0.07
    :CGRectMake
    0.07
     collapsing
    0.07
     commitment
    0.06
    Shar
    0.06
    VertexAttribArray
    0.06
    (internal
    0.06
     lô
    0.06
    'I
    0.06
    Act Density 0.577%

    No Known Activations