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

    Neuronpedia

    INDEX
    Explanations

    ghost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _RING
    -0.06
    чної
    -0.06
     eing
    -0.06
    ों,
    -0.06
    .',
↵
    -0.06
    ＾
    -0.06
     Interaction
    -0.06
    까지
    -0.06
     başkan
    -0.05
    <nav
    -0.05
    POSITIVE LOGITS
     péri
    0.07
    Secret
    0.07
     Mixed
    0.07
     Secret
    0.07
     воздух
    0.07
     кілька
    0.07
    rey
    0.07
    VIDEO
    0.07
    Mixed
    0.07
     falling
    0.07
    Act Density 0.000%

    No Known Activations