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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [z
    -0.07
     之
    -0.07
     Frame
    -0.07
    uraa
    -0.07
    _hub
    -0.07
     framed
    -0.06
     opcode
    -0.06
    TextUtils
    -0.06
    _DEL
    -0.06
    itler
    -0.06
    POSITIVE LOGITS
     convoy
    0.06
     CPI
    0.06
    -aware
    0.06
    隆
    0.06
    .localStorage
    0.06
     حمایت
    0.06
    kin
    0.06
    olecular
    0.06
    WithMany
    0.06
    CALE
    0.06
    Act Density 0.034%

    No Known Activations