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

    Neuronpedia

    INDEX
    Explanations

    available

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ponce
    -0.07
     quarterback
    -0.07
     Biology
    -0.06
     Cute
    -0.06
     proximity
    -0.06
     conceded
    -0.06
     recipients
    -0.06
    legation
    -0.06
     DAYS
    -0.06
     mieux
    -0.06
    POSITIVE LOGITS
    
    0.07
     Nb
    0.07
    ATEGORY
    0.06
    õi
    0.06
    _p
    0.06
     ch
    0.06
     WideString
    0.06
     auc
    0.06
    ,tp
    0.06
    PX
    0.06
    Act Density 0.009%

    No Known Activations