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

    Neuronpedia

    INDEX
    Explanations

    4

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    drawer
    -0.07
    قضاء
    -0.07
    fee
    -0.07
    Hosting
    -0.06
    logan
    -0.06
    !",↵
    -0.06
    透過
    -0.06
    полнение
    -0.06
     photoshop
    -0.06
     stakes
    -0.06
    POSITIVE LOGITS
    ơ
    0.07
    两侧
    0.07
     integer
    0.07
     Med
    0.07
     Bust
    0.07
    terror
    0.07
    。
    0.07
    $this
    0.06
    .mass
    0.06
    sections
    0.06
    Act Density 0.340%

    No Known Activations