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

    Neuronpedia

    INDEX
    Explanations

    The

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dí
    -0.08
    苦苦
    -0.08
    켕
    -0.07
    瞫
    -0.07
    OptionsMenu
    -0.07
    딜
    -0.07
    .sem
    -0.07
    专注
    -0.07
    迷失
    -0.07
    (codec
    -0.07
    POSITIVE LOGITS
     التركي
    0.07
     Lik
    0.07
     carrots
    0.07
    charge
    0.07
    (has
    0.07
     funcionários
    0.07
     infos
    0.06
    جان
    0.06
    Adding
    0.06
     hasattr
    0.06
    Act Density 0.002%

    No Known Activations