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

    Neuronpedia

    INDEX
    Explanations

    decision-making

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chorus
    -0.07
     Uniform
    -0.07
     Muscle
    -0.07
    (selector
    -0.06
    izarre
    -0.06
    lya
    -0.06
    /ne
    -0.06
    Normal
    -0.06
     vulner
    -0.06
    stri
    -0.06
    POSITIVE LOGITS
     contested
    0.07
    (groupId
    0.06
    _expiry
    0.06
    bfd
    0.06
    EGIN
    0.06
     sextreffen
    0.06
    	next
    0.06
    	global
    0.06
     RELATED
    0.06
    _EMIT
    0.06
    Act Density 0.021%

    No Known Activations