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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     smarter
    -0.07
     questioning
    -0.06
    clip
    -0.06
     incomes
    -0.06
    ourg
    -0.06
    _documento
    -0.06
     unspecified
    -0.06
     buscar
    -0.06
    ijd
    -0.06
     enlist
    -0.06
    POSITIVE LOGITS
     thuisontvangst
    0.07
    	std
    0.07
    /std
    0.06
     δυνα
    0.06
     bắt
    0.06
    ング
    0.06
    toi
    0.06
     jugg
    0.06
    (dst
    0.06
     cerr
    0.06
    Act Density 0.135%

    No Known Activations