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

    Neuronpedia

    INDEX
    Explanations

    vac

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _comment
    -0.06
     vulnerabilities
    -0.06
    च
    -0.06
    pts
    -0.06
    MULT
    -0.06
     carrier
    -0.06
     yeni
    -0.05
    preferences
    -0.05
    '";↵
    -0.05
     tile
    -0.05
    POSITIVE LOGITS
     アイ
    0.08
    .isOn
    0.07
     Chuck
    0.07
     iTunes
    0.07
     ABOVE
    0.07
    inha
    0.06
    _TEX
    0.06
    orc
    0.06
     Cannes
    0.06
     libertarian
    0.06
    Act Density 0.001%

    No Known Activations