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

    Neuronpedia

    INDEX
    Explanations

    games

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    빠
    -0.06
    ifecycle
    -0.06
     Wh
    -0.06
    imated
    -0.06
    inha
    -0.06
    ated
    -0.06
     smoked
    -0.06
     odpowied
    -0.06
    rupt
    -0.06
    ruption
    -0.06
    POSITIVE LOGITS
     января
    0.07
     lesbische
    0.07
     Continuing
    0.07
     Else
    0.07
     проекту
    0.06
    -го
    0.06
    γέν
    0.06
     isnt
    0.06
    .city
    0.06
     регулю
    0.06
    Act Density 0.309%

    No Known Activations