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

    Neuronpedia

    INDEX
    Explanations

    urls or codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    》。
    0.26
    🩷
    0.24
     침
    0.22
     серии
    0.22
    }$).
    0.22
     пита
    0.21
    Sexo
    0.21
    ״
    0.21
     시작
    0.21
    。」
    0.20
    POSITIVE LOGITS
     Generator
    0.24
    b
    0.23
    ns
    0.23
    ங்கு
    0.22
    na
    0.22
    itative
    0.22
     Wizards
    0.22
    非常有
    0.22
     Pipeline
    0.21
     Virtual
    0.21
    Act Density 0.022%

    No Known Activations