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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    oras
    -0.07
     carrera
    -0.06
    (loss
    -0.06
    _pd
    -0.06
     đèn
    -0.06
    #print
    -0.06
     discount
    -0.06
     brokers
    -0.06
     shock
    -0.06
    POSITIVE LOGITS
     Simply
    0.09
                                   ↵
    0.07
     fatty
    0.06
     Saying
    0.06
    	ERR
    0.06
    	Vec
    0.06
    ::↵
    0.06
    ulerAngles
    0.06
    衣
    0.06
    efined
    0.06
    Act Density 0.014%

    No Known Activations