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

    Neuronpedia

    INDEX
    Explanations

    driven by a need or desire

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ম্বা
    0.47
     modifying
    0.47
     använder
    0.45
     using
    0.44
     basing
    0.43
    TRAILING
    0.43
    使用
    0.42
     utilizing
    0.42
     базы
    0.41
     disregarding
    0.41
    POSITIVE LOGITS
     curiosity
    0.55
     궁금
    0.53
     visions
    0.52
     perguntas
    0.50
     necessità
    0.50
     thoughts
    0.50
     rumors
    0.50
     rumours
    0.50
     nevoia
    0.50
     delusions
    0.49
    Act Density 0.027%

    No Known Activations