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

    Neuronpedia

    INDEX
    Explanations

    .img files or activation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ESSION
    0.58
     іх
    0.57
     starved
    0.57
     노력
    0.56
     disdain
    0.56
     obese
    0.56
    xception
    0.55
     unrelenting
    0.55
     înce
    0.55
     мали
    0.55
    POSITIVE LOGITS
    Up
    0.62
    S
    0.59
    Rid
    0.58
    List
    0.56
    Repository
    0.56
    D
    0.56
    En
    0.55
    G
    0.55
    Sp
    0.55
    V
    0.53
    Act Density 0.000%

    No Known Activations