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

    Neuronpedia

    INDEX
    Explanations

    code/technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Roskov
    -0.66
    شهاد
    -0.64
     defaultstate
    -0.57
    ⓧ
    -0.56
    tagHelperRunner
    -0.53
    期刊论文
    -0.48
    mandu
    -0.48
     initComponents
    -0.47
     GenerationType
    -0.47
     intptr
    -0.47
    POSITIVE LOGITS
    Trimethyl
    0.55
    FilterChain
    0.54
    ]._
    0.52
    EDEFAULT
    0.52
     Amos
    0.52
    Amos
    0.52
     Against
    0.50
    Against
    0.50
    /*:
    0.50
    المناصب
    0.50
    Act Density 0.008%

    No Known Activations