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

    Neuronpedia

    INDEX
    Explanations

    α

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scouting
    -0.07
     fing
    -0.07
    璞
    -0.07
     �
    -0.07
    (Mod
    -0.07
    atto
    -0.07
    ceil
    -0.07
    -sign
    -0.06
    -0.06
     kö
    -0.06
    POSITIVE LOGITS
    今回
    0.07
    ippers
    0.07
    が多く
    0.07
    .concatenate
    0.07
    ثير
    0.07
     Monday
    0.07
    esterday
    0.07
     Modes
    0.07
    (quantity
    0.06
    .alias
    0.06
    Act Density 0.000%

    No Known Activations