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

    Neuronpedia

    INDEX
    Explanations

    OFF

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     professional
    0.26
     girlfriend
    0.25
    hole
    0.25
     esport
    0.25
     career
    0.24
    ounters
    0.24
     or
    0.24
    ise
    0.24
    anmar
    0.24
    amoto
    0.24
    POSITIVE LOGITS
     cæ
    0.28
     հ
    0.27
     bł
    0.27
    Findings
    0.26
    withId
    0.25
    }_{-}\
    0.25
     হওয়ায়
    0.25
    ਸ
    0.25
    ᆹ
    0.25
     {}\
    0.25
    Act Density 0.315%

    No Known Activations