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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     <--
    -0.07
     Glas
    -0.06
    보
    -0.06
    γι
    -0.06
    	option
    -0.06
    OTAL
    -0.06
     Filip
    -0.06
     út
    -0.06
    textarea
    -0.06
    핀
    -0.06
    POSITIVE LOGITS
    -reply
    0.07
    urma
    0.06
    smouth
    0.06
    _]
    0.06
    ↵↵↵↵↵↵
    0.06
    poč
    0.06
     Installing
    0.06
     bod
    0.06
    _optimizer
    0.05
    -,
    0.05
    Act Density 0.039%

    No Known Activations