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

    Neuronpedia

    INDEX
    Explanations

    Negative situations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Noble
    -0.08
    Around
    -0.06
     championship
    -0.06
    -quality
    -0.06
    \Has
    -0.06
    Christian
    -0.06
    	emit
    -0.06
     stanov
    -0.06
    (sequence
    -0.06
    şa
    -0.06
    POSITIVE LOGITS
     MP
    0.07
    aney
    0.07
    اق
    0.07
    _FILENO
    0.07
     ############################################################################
    0.06
    yscale
    0.06
     pioneered
    0.06
    _COM
    0.06
     kissing
    0.06
    .itemId
    0.06
    Act Density 0.293%

    No Known Activations