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

    Neuronpedia

    INDEX
    Explanations

    taste

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _TestCase
    -0.07
    arking
    -0.07
     probing
    -0.07
     Reason
    -0.07
    icích
    -0.07
    calls
    -0.06
    rians
    -0.06
    iless
    -0.06
    νοντας
    -0.06
    _MEMBERS
    -0.06
    POSITIVE LOGITS
    。本
    0.06
     determines
    0.06
    	Duel
    0.06
     vx
    0.06
     NSTextAlignment
    0.06
    appoint
    0.06
    _here
    0.06
    	comment
    0.06
    sth
    0.06
    ');
↵
    0.06
    Act Density 0.009%

    No Known Activations