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
    ivan
    -0.07
    first
    -0.07
    oğan
    -0.07
    과의
    -0.06
    dom
    -0.06
    akens
    -0.06
    �
    -0.06
    Когда
    -0.06
    Ek
    -0.06
     tôi
    -0.06
    POSITIVE LOGITS
     thrown
    0.07
    (ti
    0.07
     stout
    0.07
     defeated
    0.06
     coment
    0.06
    ripsi
    0.06
     Wins
    0.06
     combust
    0.06
     outfield
    0.06
     perso
    0.06
    Act Density 0.006%

    No Known Activations