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

    Neuronpedia

    INDEX
    Explanations

    Book

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _selector
    -0.06
    current
    -0.06
    subseteq
    -0.06
    	A
    -0.06
     slipping
    -0.06
    -radio
    -0.06
    Federal
    -0.06
    	pos
    -0.06
     потом
    -0.06
    _cases
    -0.06
    POSITIVE LOGITS
     ◆
    0.07
    .AbsoluteConstraints
    0.06
     witch
    0.06
     publik
    0.06
    耶
    0.06
     campaigning
    0.06
     ดาว
    0.06
     crunch
    0.06
     cre
    0.06
     erotik
    0.06
    Act Density 0.372%

    No Known Activations