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

    Neuronpedia

    INDEX
    Explanations

    Dichotomy of Control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelAndView
    0.40
     চুলের
    0.40
    ;%(
    0.39
    .<
    0.39
    .`);
    0.39
    后期
    0.38
     makarna
    0.38
     gönder
    0.38
    ESTER
    0.38
    털
    0.38
    POSITIVE LOGITS
    buff
    0.44
    NYSE
    0.41
    tic
    0.40
    l
    0.40
    d
    0.40
    Cliff
    0.39
    a
    0.39
    fi
    0.39
    lif
    0.39
    moil
    0.39
    Act Density 0.001%

    No Known Activations