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

    Neuronpedia

    INDEX
    Explanations

    her breasts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    েন্দু
    0.40
    =".$
    0.39
    ᅲ
    0.38
     flavon
    0.38
     diaphrag
    0.38
    ColorF
    0.37
    Hb
    0.37
     काग
    0.37
     papaya
    0.37
    响应
    0.36
    POSITIVE LOGITS
     sot
    0.40
    oplayer
    0.39
    pl
    0.38
    comic
    0.38
     спа
    0.38
    bible
    0.38
    ện
    0.37
    umab
    0.37
     optimum
    0.36
     entier
    0.36
    Act Density 0.001%

    No Known Activations