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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tableName
    -0.06
    sian
    -0.06
     FIG
    -0.06
     hely
    -0.06
     euch
    -0.06
     nhiều
    -0.06
     fis
    -0.06
     Too
    -0.06
    ออกแบบ
    -0.06
     таких
    -0.06
    POSITIVE LOGITS
    拳
    0.07
    _MAJOR
    0.06
    ALLENG
    0.06
     Crusher
    0.06
     jailed
    0.06
    254
    0.06
    plier
    0.06
    .setAttribute
    0.06
    pliers
    0.06
    AGEMENT
    0.06
    Act Density 0.186%

    No Known Activations