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

    Neuronpedia

    INDEX
    Explanations

    arrange private babysitting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     DateTime
    0.48
     Governing
    0.44
     geweld
    0.43
    dylib
    0.43
     Controls
    0.42
     Gonna
    0.42
     NYC
    0.41
     Ainsi
    0.40
    就不会
    0.39
     circuits
    0.39
    POSITIVE LOGITS
    А
    0.55
    Ο
    0.50
    methoxy
    0.50
    Aust
    0.48
    им
    0.46
    Ap
    0.46
    kü
    0.46
     wip
    0.45
    Hel
    0.44
    0.44
    Act Density 0.002%

    No Known Activations