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

    Neuronpedia

    INDEX
    Explanations

    way,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ugan
    0.41
    frm
    0.40
    izumab
    0.39
    কিন
    0.38
    ion
    0.38
    ர்த
    0.38
     mathematically
    0.37
    und
    0.37
    align
    0.37
     புத்த
    0.37
    POSITIVE LOGITS
     appealing
    0.40
     ಹೃ
    0.38
    ↪
    0.37
     Knob
    0.37
     Kapit
    0.36
     obes
    0.36
    ᅦ
    0.36
     діа
    0.36
     คง
    0.36
     snee
    0.35
    Act Density 0.002%

    No Known Activations