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
    	RTCK
    -0.07
    :)];↵
    -0.07
     свій
    -0.07
    _already
    -0.07
     друз
    -0.06
     запис
    -0.06
     disrupt
    -0.06
     wooden
    -0.06
     undercover
    -0.06
    ­ing
    -0.06
    POSITIVE LOGITS
    (level
    0.06
    .training
    0.06
     част
    0.06
     Nietzsche
    0.06
    hir
    0.06
    inality
    0.06
    (server
    0.06
     Fang
    0.06
    983
    0.06
    �始化
    0.06
    Act Density 0.000%

    No Known Activations