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

    Neuronpedia

    INDEX
    Explanations

    feet

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jind
    0.60
    吕
    0.57
    怏
    0.56
    ገ
    0.55
    phonic
    0.55
     Screen
    0.55
     коро
    0.54
    phas
    0.54
     kink
    0.53
     screen
    0.52
    POSITIVE LOGITS
     foot
    4.15
     feet
    3.91
     Foot
    3.77
    Foot
    3.66
    foot
    3.64
     Feet
    3.35
     FOOT
    3.22
    feet
    3.20
    FOOT
    3.07
    Feet
    3.02
    Act Density 0.161%

    No Known Activations