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

    Neuronpedia

    INDEX
    Explanations

    ;

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utt
    -0.07
    /repository
    -0.07
     conductivity
    -0.07
    Spawn
    -0.06
    Paid
    -0.06
    _HIDE
    -0.06
    prefix
    -0.06
     Rated
    -0.06
     Rugby
    -0.06
     condos
    -0.06
    POSITIVE LOGITS
     hoping
    0.08
     restau
    0.07
    樂
    0.06
     Doing
    0.06
     Lê
    0.06
    Mich
    0.06
    ¯¯
    0.06
     عليه
    0.06
    idl
    0.06
     развития
    0.06
    Act Density 0.082%

    No Known Activations