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

    Neuronpedia

    INDEX
    Explanations

    ility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	layout
    -0.07
    (vec
    -0.07
    (callback
    -0.07
    	attr
    -0.06
     inj
    -0.06
    ,input
    -0.06
    OH
    -0.06
     vector
    -0.06
    _lm
    -0.06
    مول
    -0.06
    POSITIVE LOGITS
    Quarter
    0.08
    那些
    0.07
    anced
    0.07
    Follow
    0.06
    .Payment
    0.06
    一個
    0.06
     enormous
    0.06
     trolls
    0.06
     Quarter
    0.06
     Annual
    0.06
    Act Density 0.093%

    No Known Activations