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

    Neuronpedia

    INDEX
    Explanations

    required

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Adv
    -0.07
     raining
    -0.07
    忽
    -0.06
    ersions
    -0.06
    Nous
    -0.06
    利用
    -0.06
     Dr
    -0.06
    rar
    -0.06
    PU
    -0.06
    ための
    -0.06
    POSITIVE LOGITS
    톤
    0.08
     forged
    0.06
    mouth
    0.06
    ίν
    0.06
    关系
    0.06
    ñ
    0.06
     Ağustos
    0.06
     گفت
    0.06
     autistic
    0.06
    LT
    0.06
    Act Density 0.000%

    No Known Activations