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

    Neuronpedia

    INDEX
    Explanations

    Spanish

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     what
    -0.06
    Weapon
    -0.06
     What
    -0.06
    Not
    -0.06
     лиш
    -0.06
     nale
    -0.06
     fully
    -0.06
     assumptions
    -0.06
     READY
    -0.06
    Yep
    -0.05
    POSITIVE LOGITS
    -UA
    0.07
    ixon
    0.07
     counterpart
    0.07
     Doom
    0.07
     点
    0.06
     ﾊ
    0.06
    .DeepEqual
    0.06
     smtp
    0.06
     Chapman
    0.06
    lerinin
    0.06
    Act Density 0.004%

    No Known Activations