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

    Neuronpedia

    INDEX
    Explanations

    Placeholder text or code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    有很大
    -0.07
     chilled
    -0.07
     Arctic
    -0.07
     Schl
    -0.07
    فز
    -0.06
    祭
    -0.06
     내
    -0.06
    矿
    -0.06
    溴
    -0.06
    ата
    -0.06
    POSITIVE LOGITS
     então
    0.07
    conut
    0.06
     SCP
    0.06
     gearing
    0.06
     doubles
    0.06
    >&
    0.06
    Compression
    0.06
     câ
    0.06
     damping
    0.06
    (&
    0.06
    Act Density 0.002%

    No Known Activations