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

    Neuronpedia

    INDEX
    Explanations

    Scientific studies and relationships

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     centers
    -0.07
     herself
    -0.07
     supports
    -0.07
     himself
    -0.06
    ，加
    -0.06
     jersey
    -0.06
    das
    -0.06
    _skip
    -0.06
    DON
    -0.06
    uplic
    -0.06
    POSITIVE LOGITS
    Με
    0.07
    Anth
    0.07
    Wizard
    0.07
     srp
    0.06
    ortal
    0.06
    �
    0.06
    erras
    0.06
    _individual
    0.06
    engo
    0.06
    .lo
    0.06
    Act Density 0.357%

    No Known Activations