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

    Neuronpedia

    INDEX
    Explanations

    content type definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    வுகளை
    0.44
    rf
    0.42
    그
    0.41
    A
    0.40
    などで
    0.39
    Après
    0.39
    ARI
    0.38
    DET
    0.38
    Right
    0.37
    거나
    0.37
    POSITIVE LOGITS
    の特徴
    0.64
     description
    0.63
     structure
    0.61
     consists
    0.61
    特点
    0.59
     specifics
    0.55
     특징
    0.54
    の種類
    0.54
     characteristics
    0.54
     består
    0.53
    Act Density 0.040%

    No Known Activations