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

    Neuronpedia

    INDEX
    Explanations

    comes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bella
    -0.07
     هي
    -0.07
    umbnail
    -0.06
     Beijing
    -0.06
     teg
    -0.06
     پزشکی
    -0.06
    .be
    -0.06
    Less
    -0.06
    _CONSTANT
    -0.05
     ตาม
    -0.05
    POSITIVE LOGITS
    (msg
    0.07
     rozum
    0.07
    _submit
    0.07
    .choices
    0.07
     attached
    0.06
    ngoing
    0.06
    [:
    0.06
    .listen
    0.06
     EVER
    0.06
     nichts
    0.06
    Act Density 0.010%

    No Known Activations