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

    Neuronpedia

    INDEX
    Explanations

    -license

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Compact
    -0.07
    .Sub
    -0.06
    til
    -0.06
    _uv
    -0.06
    ached
    -0.06
     ｜
    -0.06
    _Sh
    -0.06
     十
    -0.06
     hass
    -0.06
     IPC
    -0.06
    POSITIVE LOGITS
    -license
    0.12
     politic
    0.08
    ヶ月
    0.07
     Foundation
    0.07
    ительным
    0.07
     Slots
    0.07
    τι
    0.07
     мет
    0.06
    imize
    0.06
    binding
    0.06
    Act Density 0.000%

    No Known Activations