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

    Neuronpedia

    INDEX
    Explanations

    ships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Of
    -0.06
     interpret
    -0.06
     mentoring
    -0.06
    doctor
    -0.06
     desar
    -0.06
     Peng
    -0.06
    (ErrorMessage
    -0.06
    /var
    -0.06
     як
    -0.06
     escri
    -0.06
    POSITIVE LOGITS
    DS
    0.07
    orges
    0.06
    ifes
    0.06
    duto
    0.06
    APS
    0.06
    uggage
    0.06
    -plus
    0.06
    _values
    0.06
    usalem
    0.06
    ане
    0.06
    Act Density 0.036%

    No Known Activations