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

    Neuronpedia

    INDEX
    Explanations

    twitter handles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     comedian
    0.61
     singer
    0.58
     @
    0.57
     Actor
    0.54
    /@
    0.52
     rapper
    0.50
     "@
    0.50
    blogspot
    0.49
     @_
    0.49
     actriz
    0.48
    POSITIVE LOGITS
    }}}}$
    0.38
    permutation
    0.38
     markers
    0.38
    \"{
    0.37
    ,<
    0.35
     হাদী
    0.35
     clip
    0.35
    குறி
    0.35
    Edit
    0.35
    莧
    0.35
    Act Density 0.001%

    No Known Activations