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

    Neuronpedia

    INDEX
    Explanations

    forward command

    np_max-act · gemini-2.0-flash

    This neuron responds to numeric literals containing decimal points (floating-point numbers).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .Geometry
    -0.07
     визначення
    -0.06
    �果
    -0.06
     عزیز
    -0.06
     afore
    -0.06
     Leonardo
    -0.06
     แ
    -0.06
    "profile
    -0.06
    ونه
    -0.06
     labels
    -0.06
    POSITIVE LOGITS
    ==>
    0.07
    (This
    0.07
     bağımsız
    0.06
     bapt
    0.06
    TRACK
    0.06
    ’h
    0.06
     COOKIE
    0.06
    áh
    0.06
     armed
    0.06
     summ
    0.06
    Act Density 0.004%

    No Known Activations