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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    很快就
    -0.07
    ʕ
    -0.07
    书写
    -0.07
    꽂
    -0.07
    뽄
    -0.07
    :Is
    -0.06
    /search
    -0.06
    ↛
    -0.06
    ᒌ
    -0.06
    shiv
    -0.06
    POSITIVE LOGITS
    	rs
    0.08
    &quot
    0.08
     지난
    0.07
    乃至
    0.07
     incident
    0.07
    рег
    0.07
    사업
    0.07
    target
    0.07
    ildo
    0.07
     Hibernate
    0.07
    Act Density 0.000%

    No Known Activations