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
    jectives
    -0.08
     themes
    -0.07
     human
    -0.07
    vrd
    -0.07
    こんな
    -0.06
    _costs
    -0.06
     Cors
    -0.06
     screening
    -0.06
    /slider
    -0.06
     prospects
    -0.06
    POSITIVE LOGITS
     writable
    0.07
    Ｅ
    0.07
     움직
    0.07
    (coeffs
    0.07
    (.)
    0.06
     sürede
    0.06
     Lesb
    0.06
     ◑
    0.06
    Nic
    0.06
     kazan
    0.06
    Act Density 0.001%

    No Known Activations