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

    Neuronpedia

    INDEX
    Explanations

    beginning of articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    能源
    -0.07
    	bool
    -0.07
    _repo
    -0.07
     pieces
    -0.07
    seq
    -0.07
    _mask
    -0.06
    ůj
    -0.06
     absorb
    -0.06
     penetrate
    -0.06
    .hit
    -0.06
    POSITIVE LOGITS
     поскольку
    0.06
    (email
    0.06
    ۱۹۶
    0.06
     Funny
    0.06
    *dx
    0.06
    (paren
    0.06
    qw
    0.06
    ,status
    0.06
    bron
    0.06
    "(
    0.05
    Act Density 0.113%

    No Known Activations