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

    Neuronpedia

    INDEX
    Explanations

    decisions related

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಖರೀದ
    0.81
     cram
    0.76
    Prova
    0.75
    GameState
    0.75
    <unused441>
    0.74
     Hör
    0.73
    विटी
    0.73
    Pron
    0.73
     separated
    0.71
    Datetime
    0.71
    POSITIVE LOGITS
     Rel
    1.01
     Relative
    0.95
    Rel
    0.95
    rel
    0.93
     relative
    0.93
    Relative
    0.92
     relativo
    0.89
     relat
    0.88
     rel
    0.88
    relative
    0.85
    Act Density 0.014%

    No Known Activations