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

    Neuronpedia

    INDEX
    Explanations

    code and formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imi
    -0.06
     cylindrical
    -0.06
    藍
    -0.06
     الد
    -0.06
    �
    -0.06
     není
    -0.06
    �
    -0.06
    burst
    -0.06
    ingu
    -0.06
     ValueType
    -0.06
    POSITIVE LOGITS
     teleport
    0.07
     approval
    0.07
    ían
    0.07
    _is
    0.07
    inputEmail
    0.07
    -trash
    0.06
    ia
    0.06
     Hort
    0.06
    ']);
    0.06
    -sponsored
    0.06
    Act Density 0.025%

    No Known Activations