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

    Neuronpedia

    INDEX
    Explanations

    Hammer Curls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Centered
    0.39
    Instance
    0.39
     இய
    0.38
    Her
    0.38
     نت
    0.36
    centered
    0.36
    Cream
    0.36
    Premier
    0.36
    Unknown
    0.36
    Threat
    0.36
    POSITIVE LOGITS
     Tabor
    0.38
     ei
    0.37
     sheep
    0.35
    ucker
    0.35
     Tach
    0.35
    agliari
    0.34
     spind
    0.34
     impec
    0.33
     stall
    0.33
     correspondingly
    0.33
    Act Density 0.000%

    No Known Activations