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

    Neuronpedia

    INDEX
    Explanations

    list items or code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    3.82
    (
    3.05
    （
    3.03
     （
    2.76
     ((
    2.71
     ([
    2.41
    ((
    2.29
     (<
    2.28
    '(
    2.27
     (~
    2.27
    POSITIVE LOGITS
    ╯
    0.80
    මට
    0.80
    वू
    0.79
    <blockquote>
    0.76
    
    0.75
    ◎
    0.75
    }=$
    0.74
    ෙන්ම
    0.73
    之後
    0.71
    codiles
    0.70
    Act Density 0.553%

    No Known Activations