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

    Neuronpedia

    INDEX
    Explanations

    Leadership, mentoring, grant funding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     horr
    0.49
     macho
    0.47
     blobs
    0.45
     brute
    0.45
     bizarre
    0.44
     monstrous
    0.44
     fantastical
    0.43
     snar
    0.43
     cheaply
    0.43
     object
    0.43
    POSITIVE LOGITS
     Leadership
    0.75
     المشار
    0.73
     leadership
    0.68
     экспер
    0.68
     mentoring
    0.68
     участия
    0.68
     participates
    0.67
    Leadership
    0.67
     participated
    0.67
    particip
    0.67
    Act Density 0.012%

    No Known Activations