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
    .features
    -0.07
     Similar
    -0.07
    .uri
    -0.07
     inflated
    -0.06
     Compute
    -0.06
    messages
    -0.06
    配
    -0.06
    _activities
    -0.06
    	DBG
    -0.06
    ;|
    -0.06
    POSITIVE LOGITS
     predator
    0.07
     læ
    0.07
    แป
    0.06
     la
    0.06
     Voc
    0.06
    ับค
    0.06
    ôn
    0.06
    真是
    0.06
    ]);
↵
    0.06
     preco
    0.06
    Act Density 0.007%

    No Known Activations