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

    Neuronpedia

    INDEX
    Explanations

    Code documentation/parameters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PAR
    -0.07
    _contract
    -0.07
     relax
    -0.07
    -0.07
     NRA
    -0.06
     basement
    -0.06
     Part
    -0.06
     agrees
    -0.06
    Sites
    -0.06
     loved
    -0.06
    POSITIVE LOGITS
     DBG
    0.07
    ับค
    0.07
     Generate
    0.07
    viso
    0.06
    던
    0.06
    иж
    0.06
    の方
    0.06
    lah
    0.06
    quipment
    0.06
    ="'+
    0.06
    Act Density 0.003%

    No Known Activations