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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     quatre
    -0.07
     deser
    -0.07
    IRA
    -0.07
    Uno
    -0.06
     dane
    -0.06
     만들어
    -0.06
    *pi
    -0.06
     dados
    -0.06
    _email
    -0.06
    _tree
    -0.06
    POSITIVE LOGITS
    -covered
    0.08
    Healthy
    0.07
    akis
    0.07
     Officer
    0.07
    ablo
    0.07
    through
    0.07
    �
    0.07
    ([
    0.06
    ({
    0.06
    …↵
    0.06
    Act Density 0.010%

    No Known Activations