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

    Neuronpedia

    INDEX
    Explanations

    Parts of the body

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⍣
    -0.08
    王国
    -0.07
    (Collision
    -0.07
     trip
    -0.06
    רכיב
    -0.06
    Nonce
    -0.06
     PhoneNumber
    -0.06
     province
    -0.06
    تكلم
    -0.06
     Cement
    -0.06
    POSITIVE LOGITS
    .setError
    0.08
    ulares
    0.08
    淚
    0.08
    _ta
    0.07
     vere
    0.07
    ernetes
    0.07
    ✒
    0.07
    _userdata
    0.07
     đáp
    0.07
    ڱ
    0.06
    Act Density 0.048%

    No Known Activations