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

    Neuronpedia

    INDEX
    Explanations

    part of a process

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     glimpses
    0.40
    рее
    0.39
     স্থানে
    0.38
     insights
    0.37
    róleo
    0.37
     Jia
    0.36
     Dend
    0.36
    ળે
    0.36
     words
    0.36
     megfelel
    0.36
    POSITIVE LOGITS
     repertoire
    0.73
     arsenal
    0.67
     equation
    0.59
     lore
    0.57
    的一部分
    0.57
     iconography
    0.55
    equation
    0.53
     toolkit
    0.53
    pertoire
    0.53
     repert
    0.53
    Act Density 0.022%

    No Known Activations