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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     streets
    -0.07
     crushing
    -0.07
    forth
    -0.06
     numbers
    -0.06
     Harm
    -0.06
    Van
    -0.06
    ikut
    -0.06
     Vu
    -0.06
    尿
    -0.06
    _ids
    -0.06
    POSITIVE LOGITS
     statewide
    0.07
    -co
    0.06
    .viewport
    0.06
     prat
    0.06
    _clicked
    0.06
     этому
    0.06
    contres
    0.06
    ща
    0.06
    ucson
    0.06
    0.06
    Act Density 0.163%

    No Known Activations