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

    Neuronpedia

    INDEX
    Explanations

    nerve, nervous, endings, function, agent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AMO
    0.39
    阌
    0.39
    Learning
    0.38
    omn
    0.38
    angnya
    0.38
    Kerry
    0.38
    negative
    0.38
    Negative
    0.37
    Deferred
    0.37
     omn
    0.37
    POSITIVE LOGITS
     nerve
    0.92
     Nerve
    0.87
     Nerv
    0.81
     nerv
    0.80
     nerves
    0.75
     нер
    0.73
     endings
    0.72
     wreck
    0.68
     nerfs
    0.64
     nervoso
    0.64
    Act Density 0.005%

    No Known Activations