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

    Neuronpedia

    INDEX
    Explanations

    Password security

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    الته
    -0.07
    assage
    -0.07
    ра
    -0.06
     suchen
    -0.06
     занима
    -0.06
     metabol
    -0.06
    상을
    -0.06
     האמריק
    -0.06
     maple
    -0.06
     prospects
    -0.06
    POSITIVE LOGITS
     Oc
    0.07
    AndHashCode
    0.07
    多次
    0.07
    扭曲
    0.07
    Nib
    0.07
     viewpoint
    0.07
     Templates
    0.07
     cdr
    0.07
     sid
    0.07
    yt
    0.07
    Act Density 0.021%

    No Known Activations