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

    Neuronpedia

    INDEX
    Explanations

    history goes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     كلام
    0.62
     mirip
    0.57
     tweaks
    0.54
     😂
    0.54
     진짜
    0.54
     devs
    0.54
    😂
    0.54
     Philly
    0.52
     quirks
    0.52
     jeśli
    0.51
    POSITIVE LOGITS
     strategically
    0.79
     diversified
    0.73
     proud
    0.70
     strategic
    0.68
     strives
    0.68
     esteemed
    0.68
     endeavoured
    0.66
    実績
    0.66
     established
    0.64
     striving
    0.64
    Act Density 0.001%

    No Known Activations