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

    Neuronpedia

    INDEX
    Explanations

    self-talk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cops
    -0.07
     Ion
    -0.07
    给我
    -0.06
    LOOK
    -0.06
    ;)
    -0.06
    BF
    -0.06
    	my
    -0.06
     Angie
    -0.06
    pering
    -0.06
     HALF
    -0.06
    POSITIVE LOGITS
     хви
    0.07
     počet
    0.07
     действия
    0.06
    ezpe
    0.06
    饮
    0.06
    (IDC
    0.06
     بسیار
    0.06
     sangat
    0.06
    .space
    0.06
     prostoru
    0.06
    Act Density 0.043%

    No Known Activations