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

    Neuronpedia

    INDEX
    Explanations

    Before a specific time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     는
    -0.09
    reb
    -0.08
     ಬಳ
    -0.07
     للو
    -0.07
     사용
    -0.07
    -0.07
     வை
    -0.07
     sedan
    -0.07
    .ne
    -0.07
     הנה
    -0.07
    POSITIVE LOGITS
     מראש
    0.13
     заранее
    0.13
     beforehand
    0.12
     predetermined
    0.10
     adelant
    0.09
    'avance
    0.09
    性色
    0.09
     tevoren
    0.09
    公布
    0.08
     outset
    0.08
    Act Density 0.014%
    No Known Activations