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

    Neuronpedia

    INDEX
    Explanations

    Signal Protocol and Replication Policy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     realice
    0.57
     acabou
    0.55
     acabó
    0.52
     spost
    0.51
     batalha
    0.51
     alerta
    0.51
     desag
    0.51
    ونه
    0.50
     predstavlja
    0.50
     darse
    0.49
    POSITIVE LOGITS
    銀行
    0.49
     Spinal
    0.47
     bureaus
    0.46
     Serious
    0.45
    Court
    0.45
     Billboard
    0.44
     Sentence
    0.44
    es
    0.44
     Automobile
    0.44
    device
    0.44
    Act Density 0.000%

    No Known Activations