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

    Neuronpedia

    INDEX
    Explanations

    Question procedures issues

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    алет
    0.63
     flawless
    0.62
     നിറ
    0.60
     hampir
    0.60
     rif
    0.59
     miniature
    0.58
     hozzá
    0.57
     pelayanan
    0.57
     huile
    0.57
    殻
    0.56
    POSITIVE LOGITS
    Proced
    0.63
    Question
    0.63
    Bishop
    0.59
     Proced
    0.58
     Bishop
    0.55
     Josep
    0.55
    Issue
    0.54
    Recovery
    0.54
    Joseph
    0.54
    Jose
    0.53
    Act Density 0.000%

    No Known Activations