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

    Neuronpedia

    INDEX
    Explanations

    physical touch and massage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    !
    0.51
     vatten
    0.47
    äl
    0.46
    کام
    0.46
    än
    0.45
    azi
    0.44
    ད
    0.44
    geq
    0.44
    äk
    0.43
    IONAL
    0.42
    POSITIVE LOGITS
    ي
    0.63
     руки
    0.60
    ↵
    0.59
     рукой
    0.53
    压
    0.48
    લ
    0.48
     manipul
    0.47
     руками
    0.46
     bestand
    0.46
    يق
    0.46
    Act Density 0.327%

    No Known Activations