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

    Neuronpedia

    INDEX
    Explanations

    uncommon vocabulary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fan
    -0.07
    Predicate
    -0.06
     machen
    -0.06
    でき
    -0.06
     місці
    -0.06
     Fake
    -0.06
    Ign
    -0.06
    	parameters
    -0.06
     Зав
    -0.06
     імені
    -0.06
    POSITIVE LOGITS
    MC
    0.07
    HeaderCode
    0.07
    contained
    0.07
    (styles
    0.06
    LERİ
    0.06
    prints
    0.06
     рух
    0.06
    ahun
    0.06
     defaultMessage
    0.06
    š
    0.06
    Act Density 0.000%

    No Known Activations