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

    Neuronpedia

    INDEX
    Explanations

    generating specific examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    id
    0.51
    ta
    0.49
    r
    0.49
    c
    0.48
    x
    0.47
    dinger
    0.46
    teil
    0.45
    wur
    0.45
    wicket
    0.45
    in
    0.43
    POSITIVE LOGITS
    ⟋
    0.51
    屶
    0.48
     silhouette
    0.48
    ificato
    0.47
     Neust
    0.47
     Bharati
    0.47
     displace
    0.46
     ICF
    0.46
     لندن
    0.46
     Palt
    0.46
    Act Density 0.000%

    No Known Activations