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

    Neuronpedia

    INDEX
    Explanations

    legal/official procedures/fixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rections
    -0.07
     zombies
    -0.07
     plo
    -0.07
     DET
    -0.07
     Studi
    -0.07
     Richie
    -0.07
     Ele
    -0.07
    Folder
    -0.06
     thiết
    -0.06
    pty
    -0.06
    POSITIVE LOGITS
     vois
    0.06
    acja
    0.06
    -add
    0.06
    _job
    0.06
     заключ
    0.06
    _copy
    0.06
    .JsonProperty
    0.06
    _return
    0.05
    เตอร
    0.05
     inverse
    0.05
    Act Density 0.000%

    No Known Activations