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

    Neuronpedia

    INDEX
    Explanations

    Computer access

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ח
    -0.07
    ial
    -0.07
    -cal
    -0.06
    //↵↵
    -0.06
     illustrations
    -0.06
    }]
    -0.06
    eč
    -0.06
    цу
    -0.06
     Px
    -0.06
    -page
    -0.06
    POSITIVE LOGITS
     перш
    0.06
    ronym
    0.06
    RARY
    0.06
     prelim
    0.06
     безопас
    0.06
    παίδ
    0.06
     سلس
    0.06
    通過
    0.06
    .DialogResult
    0.06
     experimented
    0.06
    Act Density 0.048%

    No Known Activations