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

    Neuronpedia

    INDEX
    Explanations

    produce, emit, generate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    DefaultValue
    -0.06
     Opt
    -0.06
    ざ
    -0.06
    noc
    -0.06
    екси
    -0.06
    чення
    -0.06
     těž
    -0.06
    庫
    -0.06
     adoles
    -0.06
     prefer
    -0.05
    POSITIVE LOGITS
    Diagnostic
    0.07
    Imm
    0.07
     můj
    0.07
     cms
    0.07
    Skip
    0.06
    夢
    0.06
    اسان
    0.06
    ÄŸ
    0.06
     졸
    0.06
    _DISP
    0.06
    Act Density 0.057%

    No Known Activations