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

    Neuronpedia

    INDEX
    Explanations

    instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xB
    -0.06
    ramework
    -0.06
     choked
    -0.06
    	cnt
    -0.06
     又
    -0.06
    够
    -0.06
    告诉
    -0.06
    .length
    -0.06
    _assigned
    -0.06
    yecto
    -0.06
    POSITIVE LOGITS
    _UNDEF
    0.07
    Vec
    0.07
     Sav
    0.06
    ữ
    0.06
    NONE
    0.06
     Jan
    0.06
    _spawn
    0.06
     Dost
    0.06
     --------------------------------------------------------------------------↵
    0.06
    як
    0.06
    Act Density 0.149%

    No Known Activations