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

    Neuronpedia

    INDEX
    Explanations

    ranging from options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kod
    0.68
     बे
    0.68
     sok
    0.66
     Kod
    0.65
     grantResults
    0.64
     beams
    0.63
    Kod
    0.63
    erts
    0.62
     signals
    0.61
    Admin
    0.61
    POSITIVE LOGITS
    cję
    0.64
    ంటే
    0.59
    cparam
    0.58
    itake
    0.57
    Penalty
    0.57
     heart
    0.55
    ಪ್
    0.55
     কাপ
    0.54
    Pk
    0.54
    PUB
    0.53
    Act Density 0.046%

    No Known Activations