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

    Neuronpedia

    INDEX
    Explanations

    instance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DataGridView
    -0.07
    ича
    -0.07
    pickup
    -0.06
    ственно
    -0.06
    (Collision
    -0.06
    -plane
    -0.06
    PN
    -0.06
     CSR
    -0.06
     Selection
    -0.06
    oling
    -0.06
    POSITIVE LOGITS
     니
    0.07
    _unsigned
    0.06
    나요
    0.06
    getOrElse
    0.06
    archical
    0.06
     pathway
    0.06
     열
    0.06
    ビ
    0.06
    Byte
    0.06
     Conditions
    0.06
    Act Density 0.158%

    No Known Activations