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

    Neuronpedia

    INDEX
    Explanations

    head held high

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Identifier
    0.50
    Listener
    0.49
    Listeners
    0.48
    Book
    0.47
    Palest
    0.46
     Genet
    0.46
    lette
    0.45
    Bib
    0.45
    Producer
    0.45
    Lit
    0.45
    POSITIVE LOGITS
     diciembre
    0.55
     novembro
    0.55
     niedr
    0.52
    ंसाठी
    0.51
     jams
    0.50
    стояния
    0.49
    す
    0.49
     rendah
    0.49
    которы
    0.49
    マンス
    0.48
    Act Density 0.000%

    No Known Activations