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

    Neuronpedia

    INDEX
    Explanations

    rating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bas
    -0.07
     Blank
    -0.06
    series
    -0.06
    isspace
    -0.06
     Stop
    -0.06
     alternatives
    -0.05
    til
    -0.05
     Subtract
    -0.05
     brun
    -0.05
    وس
    -0.05
    POSITIVE LOGITS
    pun
    0.07
    HEME
    0.06
    idge
    0.06
    AndServe
    0.06
     naše
    0.06
    _DECL
    0.06
     svým
    0.06
     �
    0.06
    (per
    0.06
     Zurich
    0.06
    Act Density 0.011%

    No Known Activations