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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sb
    -0.08
     STORE
    -0.07
    TAB
    -0.07
    โช
    -0.07
    _OT
    -0.07
    Bus
    -0.06
    _dc
    -0.06
     혼
    -0.06
     survive
    -0.06
     δημιουργ
    -0.06
    POSITIVE LOGITS
     linking
    0.06
    ";
↵
    0.06
    ал
    0.06
     unlikely
    0.06
     
↵ 
↵
    0.06
     Romance
    0.06
     Apart
    0.06
     timely
    0.06
    **↵↵
    0.06
    /';↵↵
    0.06
    Act Density 0.010%

    No Known Activations