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

    Neuronpedia

    INDEX
    Explanations

    substances, supplements, and additives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     porch
    0.52
    0.51
     sheltered
    0.49
     eighties
    0.48
     kaleidoscopic
    0.47
     quake
    0.47
     prolific
    0.46
     spa
    0.45
     porcelain
    0.45
     aurora
    0.45
    POSITIVE LOGITS
    K
    0.64
    ك
    0.59
    си
    0.59
    К
    0.58
    T
    0.55
    ’
    0.55
    companies
    0.52
    ro
    0.52
    كار
    0.51
    chemicals
    0.50
    Act Density 0.301%

    No Known Activations