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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    èĬ
    -0.27
    jÄĻ
    -0.27
    婪
    -0.26
    رÙĪس
    -0.25
    urret
    -0.25
     Stored
    -0.24
    Pt
    -0.24
     Innoc
    -0.24
    LG
    -0.24
    管çIJĨå·¥ä½ľ
    -0.24
    POSITIVE LOGITS
     bund
    0.30
    -bars
    0.28
    è®®
    0.27
    son
    0.26
    ãĤĤãģ®ãģ§ãģĻ
    0.25
     ];↵↵
    0.25
     momentum
    0.24
    counts
    0.24
    çī¦
    0.24
    .memo
    0.24
    Act Density 0.015%

    No Known Activations