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

    Neuronpedia

    INDEX
    Explanations

    art physics philosophy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    809
    -0.07
    833
    -0.07
    emb
    -0.06
    _enemy
    -0.06
     species
    -0.06
     رس
    -0.06
    909
    -0.06
     compte
    -0.06
    olate
    -0.06
     reflux
    -0.06
    POSITIVE LOGITS
     watermark
    0.07
     할인
    0.06
     dlou
    0.06
     şeh
    0.06
     Disp
    0.06
     Resets
    0.06
    discount
    0.06
     prostoru
    0.06
    TECTION
    0.06
     Execution
    0.06
    Act Density 0.180%

    No Known Activations