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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indonesia
    -0.07
    Depart
    -0.06
     worksheet
    -0.06
    Invariant
    -0.06
    уг
    -0.06
    _CTX
    -0.06
    ())).
    -0.05
    .graph
    -0.05
     Miller
    -0.05
    ToPoint
    -0.05
    POSITIVE LOGITS
    160
    0.07
    Daniel
    0.06
    íte
    0.06
    icrous
    0.06
    =https
    0.06
    kers
    0.06
    greso
    0.06
    _clip
    0.06
    rw
    0.06
    here
    0.06
    Act Density 0.430%

    No Known Activations