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

    Neuronpedia

    INDEX
    Explanations

    news from Pakistan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    impact
    0.39
    Es
    0.38
     সবে
    0.37
    oprene
    0.37
     frat
    0.37
     проми
    0.37
     homelessness
    0.36
     Regex
    0.36
    space
    0.35
    frame
    0.35
    POSITIVE LOGITS
     شاہ
    0.43
     तैया
    0.42
    áneamente
    0.40
    私人
    0.40
     zahrani
    0.40
    FindFirst
    0.39
    anaa
    0.39
     नयी
    0.39
    ">•
    0.38
     রাজধান
    0.38
    Act Density 0.003%

    No Known Activations