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

    Neuronpedia

    INDEX
    Explanations

    Olympic torch/flag carrying

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .strokeStyle
    -0.08
    ἢ
    -0.07
    。www
    -0.07
     psycho
    -0.07
    שלוש
    -0.07
    eyed
    -0.07
    mse
    -0.07
     getX
    -0.07
    -lnd
    -0.06
    (varargin
    -0.06
    POSITIVE LOGITS
    موظ
    0.07
    ☒
    0.07
    アナ
    0.07
     yavaş
    0.07
     Shields
    0.07
     theatre
    0.07
    ancellation
    0.07
    أسواق
    0.07
     FF
    0.07
    Po
    0.07
    Act Density 0.004%

    No Known Activations