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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     З
    -0.07
     Buster
    -0.07
     �
    -0.07
    Stride
    -0.06
    Ctrl
    -0.06
    イ
    -0.06
    Wake
    -0.06
     ن
    -0.06
    _compile
    -0.06
    239
    -0.06
    POSITIVE LOGITS
    ouses
    0.06
     fran
    0.06
    Patient
    0.06
     sdf
    0.06
     offerings
    0.06
     Morris
    0.06
    []>(
    0.06
     firstname
    0.06
    _EDGE
    0.06
    /head
    0.05
    Act Density 0.011%

    No Known Activations