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

    Neuronpedia

    INDEX
    Explanations

    javascript require statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ;(
    0.66
     FIA
    0.65
    from
    0.64
     KIA
    0.64
    applicazione
    0.63
     Ее
    0.63
     NDR
    0.63
     RDF
    0.61
     Під
    0.61
     DPR
    0.60
    POSITIVE LOGITS
    IK
    0.68
     flexion
    0.63
    お
    0.61
    ET
    0.60
    ED
    0.55
    お届け
    0.54
    AI
    0.53
     impotence
    0.53
    대
    0.53
     restlessness
    0.52
    Act Density 0.001%

    No Known Activations