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

    Neuronpedia

    INDEX
    Explanations

    story

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    雾霾
    -0.07
    ↖
    -0.07
     nak
    -0.07
    kelig
    -0.07
    _already
    -0.07
     thrilling
    -0.07
    赶上
    -0.07
     Zhang
    -0.07
     caracter
    -0.07
     לבד
    -0.07
    POSITIVE LOGITS
    禹
    0.08
    荀
    0.07
    攻关
    0.07
    Projectile
    0.07
    Your
    0.07
    ICY
    0.06
    -product
    0.06
    理
    0.06
     assortment
    0.06
    ('&
    0.06
    Act Density 0.000%

    No Known Activations