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

    Neuronpedia

    INDEX
    Explanations

    res

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RIX
    -0.09
    🐄
    -0.07
    -Methods
    -0.07
    jące
    -0.07
    ideographic
    -0.07
     있지만
    -0.06
     ניהול
    -0.06
    ☐
    -0.06
    mph
    -0.06
    vé
    -0.06
    POSITIVE LOGITS
    Separated
    0.08
    ivalent
    0.07
     dest
    0.07
     grounded
    0.07
     annotation
    0.07
    )){
↵
    0.07
    username
    0.07
    阿拉
    0.07
    眶
    0.07
    当之无愧
    0.07
    Act Density 0.001%

    No Known Activations