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

    Neuronpedia

    INDEX
    Explanations

    math equations, derivatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     væ
    -0.06
    Implement
    -0.06
    SPORT
    -0.06
    (outfile
    -0.06
     configuring
    -0.06
    _cust
    -0.06
    買
    -0.06
    Assignable
    -0.06
     دوست
    -0.05
     práci
    -0.05
    POSITIVE LOGITS
    .Completed
    0.07
    	DBG
    0.07
     Ire
    0.07
    akra
    0.06
    Alpha
    0.06
     outgoing
    0.06
     kp
    0.06
     [],
↵
    0.06
    زه
    0.06
     happens
    0.06
    Act Density 0.002%

    No Known Activations