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

    Neuronpedia

    INDEX
    Explanations

    Finding the right person

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .learning
    -0.07
    団
    -0.07
    젝
    -0.06
    geb
    -0.06
     Gamma
    -0.06
    ème
    -0.06
    seed
    -0.06
    ضي
    -0.06
     TELE
    -0.06
    lemetry
    -0.06
    POSITIVE LOGITS
    _WATER
    0.06
     }));↵
    0.06
     consideration
    0.06
    "./
    0.06
    swing
    0.06
     lanz
    0.06
     amongst
    0.06
    laughter
    0.06
    ा↵↵
    0.06
    ksam
    0.06
    Act Density 0.030%

    No Known Activations