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

    Neuronpedia

    INDEX
    Explanations

    legal or ethical discussions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ২০১২
    0.52
     http
    0.50
     লং
    0.47
     PIR
    0.46
    http
    0.45
     නිෂ්පා
    0.44
     Pir
    0.43
     ஆரோ
    0.43
     ಉತ್ಪನ್ನ
    0.43
     ఉత్ప
    0.43
    POSITIVE LOGITS
     netizens
    0.66
     reportedly
    0.59
     allegedly
    0.59
    🥳
    0.54
    ᵉ
    0.53
     सियासी
    0.52
    🥵
    0.52
    🫶
    0.51
     semblent
    0.51
     fla
    0.49
    Act Density 0.000%

    No Known Activations