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

    Neuronpedia

    INDEX
    Explanations

    Numerical lists and ratios

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    razier
    -0.07
    .Resume
    -0.07
    ích
    -0.07
     pracowników
    -0.07
    плачива
    -0.07
    牤
    -0.07
    (peer
    -0.07
     elegant
    -0.07
    ："+
    -0.07
     Trên
    -0.07
    POSITIVE LOGITS
    -collection
    0.07
     PAS
    0.07
    _EMIT
    0.07
     thought
    0.07
    ValueChanged
    0.07
    alla
    0.06
    ida
    0.06
     �
    0.06
     Enter
    0.06
    	fun
    0.06
    Act Density 0.110%

    No Known Activations