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

    Neuronpedia

    INDEX
    Explanations

    Fellow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dsp
    -0.06
    rika
    -0.06
    @d
    -0.06
    ší
    -0.06
     bowling
    -0.06
    stri
    -0.06
     arrows
    -0.06
    Portály
    -0.06
    σμού
    -0.06
    isté
    -0.06
    POSITIVE LOGITS
     <?=
    0.07
     Fellow
    0.07
     示
    0.06
     Associate
    0.06
     Tol
    0.06
    ụy
    0.06
     căn
    0.06
    emento
    0.06
    .lon
    0.06
    ("__
    0.06
    Act Density 0.004%

    No Known Activations