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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    当做
    -0.07
     fois
    -0.07
     Online
    -0.07
    รอบ
    -0.07
    _pressed
    -0.07
     asked
    -0.06
    饺子
    -0.06
    _inside
    -0.06
     eldre
    -0.06
    上了
    -0.06
    POSITIVE LOGITS
    ბ
    0.08
     Stark
    0.07
    יקים
    0.07
    职业技能
    0.07
    (parts
    0.07
     catalog
    0.07
    .plan
    0.07
    stalk
    0.07
    沦
    0.07
     ecstatic
    0.06
    Act Density 0.008%

    No Known Activations