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

    Neuronpedia

    INDEX
    Explanations

    email regex validation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     antiserum
    0.49
    羵
    0.45
     radiologists
    0.43
    坸
    0.41
     alertness
    0.40
     tantrums
    0.40
     potholes
    0.39
     stratigraphic
    0.39
    Pig
    0.39
     NPs
    0.38
    POSITIVE LOGITS
    af
    0.45
    ce
    0.38
    cs
    0.38
    *
    0.38
    ded
    0.37
    c
    0.37
    >
    0.37
    ed
    0.37
    us
    0.37
    aced
    0.36
    Act Density 0.001%

    No Known Activations