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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gratuits
    -0.07
    _special
    -0.07
     randomly
    -0.06
     gracias
    -0.06
     Mark
    -0.06
    ethereum
    -0.06
     guided
    -0.06
     gastr
    -0.06
     ethical
    -0.06
    William
    -0.06
    POSITIVE LOGITS
    /Admin
    0.06
     stanza
    0.06
    unu
    0.06
    ってきた
    0.06
    '},
↵
    0.06
    errorMsg
    0.06
    使
    0.06
    _ENC
    0.06
    391
    0.06
    erusform
    0.06
    Act Density 0.033%

    No Known Activations