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

    Neuronpedia

    INDEX
    Explanations

    States

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _weather
    -0.06
    ائ
    -0.06
     Mas
    -0.06
     tempting
    -0.06
     liking
    -0.06
    	vec
    -0.06
    ｜
    -0.06
    ucción
    -0.06
     okres
    -0.06
    .Err
    -0.06
    POSITIVE LOGITS
    ژ
    0.07
     perceived
    0.07
    WebSocket
    0.07
    ，请
    0.06
     perceive
    0.06
    _PRED
    0.06
     Druh
    0.06
    voj
    0.06
     eligibility
    0.06
    _send
    0.06
    Act Density 0.003%

    No Known Activations