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

    Neuronpedia

    INDEX
    Explanations

    identifying official context method deviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    but
    0.36
     B
    0.35
     Rostov
    0.34
    b
    0.34
     Bari
    0.33
    Roth
    0.33
     Wirtschaft
    0.33
     Marian
    0.32
     sitcom
    0.32
     Alsace
    0.32
    POSITIVE LOGITS
    袒
    0.35
     inducement
    0.34
    르
    0.34
     の
    0.33
     embarrassment
    0.32
     milligrams
    0.31
     annoyance
    0.31
     そんな
    0.31
     hydration
    0.31
    ргә
    0.31
    Act Density 1.134%

    No Known Activations