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

    Neuronpedia

    INDEX
    Explanations

    states or sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     deportivos
    0.43
    짭
    0.43
    गरण
    0.42
    CLUDED
    0.42
    мами
    0.42
    epte
    0.41
    IKI
    0.41
     lions
    0.41
    𝘃
    0.41
    थे
    0.40
    POSITIVE LOGITS
     or
    0.47
     Weaver
    0.46
     Iris
    0.45
    ر
    0.45
     More
    0.44
     Twist
    0.44
    ის
    0.44
     Hit
    0.44
    ş
    0.43
     Irving
    0.43
    Act Density 0.002%

    No Known Activations