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

    Neuronpedia

    INDEX
    Explanations

    back

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    monds
    -0.06
    ovel
    -0.06
    ocl
    -0.06
    Credentials
    -0.06
     iso
    -0.06
     права
    -0.06
     آزمون
    -0.06
    .validators
    -0.06
    енсив
    -0.06
    (dw
    -0.06
    POSITIVE LOGITS
     Chain
    0.06
    �
    0.06
    ,lat
    0.06
     extravagant
    0.06
     صنایع
    0.06
    _make
    0.06
    _HIGH
    0.06
    ½
    0.06
    стати
    0.06
     신입
    0.06
    Act Density 0.015%

    No Known Activations