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

    Neuronpedia

    INDEX
    Explanations

    computing and culture

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     freien
    0.70
    Frozen
    0.67
     wichtigen
    0.66
     Frozen
    0.61
    Fraction
    0.59
    Freeze
    0.59
    Neigh
    0.59
    ственная
    0.57
    LFT
    0.57
    zq
    0.57
    POSITIVE LOGITS
     agrees
    0.66
     uzn
    0.64
     themes
    0.63
     findings
    0.62
     subscribed
    0.61
     темы
    0.60
    ाइज
    0.60
     anses
    0.60
     finds
    0.59
     circulated
    0.59
    Act Density 0.000%

    No Known Activations