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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    version
    -0.08
     Twice
    -0.07
    Management
    -0.07
    ]+'
    -0.07
    890
    -0.07
    メリカ
    -0.06
    ты
    -0.06
    Unified
    -0.06
     industrial
    -0.06
    사무
    -0.06
    POSITIVE LOGITS
     bpp
    0.06
     denim
    0.06
    fos
    0.06
     nederland
    0.06
     stalo
    0.06
     contradictions
    0.06
     Comey
    0.06
    Dur
    0.06
    ulong
    0.06
    oundation
    0.06
    Act Density 0.099%

    No Known Activations