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

    Neuronpedia

    INDEX
    Explanations

    &ltf

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mon
    -0.07
    ریان
    -0.07
     quần
    -0.06
     μου
    -0.06
     beaucoup
    -0.06
    ень
    -0.06
    .UTF
    -0.06
     дія
    -0.06
     갈
    -0.06
     Prairie
    -0.06
    POSITIVE LOGITS
    .clientX
    0.08
     distracting
    0.07
     Fist
    0.07
     Evidence
    0.07
     Tokens
    0.07
     shirts
    0.07
     sleepy
    0.07
     distinctive
    0.07
    Atom
    0.06
    icro
    0.06
    Act Density 0.000%

    No Known Activations