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

    Neuronpedia

    INDEX
    Explanations

    words ending in ation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mach
    0.18
    press
    0.17
    pang
    0.17
     hela
    0.17
    Mach
    0.17
    styl
    0.17
     정상
    0.17
    grads
    0.17
    b
    0.17
    z
    0.17
    POSITIVE LOGITS
    abbing
    0.24
    ouncing
    0.23
    ounsel
    0.23
    othing
    0.22
    𝒂
    0.22
    acking
    0.22
    eneral
    0.21
    unning
    0.21
    otted
    0.21
    acterial
    0.21
    Act Density 0.284%

    No Known Activations