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

    Neuronpedia

    INDEX
    Explanations

    code documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Presence
    -0.06
    θυ
    -0.06
     Μα
    -0.06
    KeyEvent
    -0.06
    水
    -0.06
    沢
    -0.06
     shortfall
    -0.06
     adaptations
    -0.06
     Apprent
    -0.06
     Ев
    -0.06
    POSITIVE LOGITS
     coz
    0.07
    alle
    0.07
     ott
    0.07
    ansas
    0.06
    áh
    0.06
    ":-
    0.06
     normalized
    0.06
    076
    0.06
    男性
    0.06
    038
    0.06
    Act Density 0.000%

    No Known Activations