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

    Neuronpedia

    INDEX
    Explanations

    acceptance of situations or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     powied
    0.67
    心配
    0.59
     সতীশ
    0.58
    cientes
    0.57
    𒁉
    0.57
    ся
    0.56
     inversiones
    0.56
     بدء
    0.56
     détect
    0.55
    ivasena
    0.55
    POSITIVE LOGITS
    Accept
    1.18
     accept
    1.05
     Accept
    1.03
     Acceptance
    1.03
     ACCEPT
    1.02
     acceptance
    1.02
     accepted
    1.01
     Accepting
    1.00
    接受
    0.96
     Accepted
    0.95
    Act Density 0.150%

    No Known Activations