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

    Neuronpedia

    INDEX
    Explanations

    pros and cons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.49
    studio
    0.48
    fter
    0.46
     hereby
    0.45
    *
    0.45
     S
    0.44
     apologize
    0.43
    5
    0.42
     studio
    0.41
     public
    0.41
    POSITIVE LOGITS
     ansiedad
    0.52
    痉
    0.51
     sintomi
    0.50
     haemorrh
    0.50
    꾿
    0.48
     uneas
    0.47
    骜
    0.46
    гови
    0.46
    数目
    0.46
    蝿
    0.46
    Act Density 0.003%

    No Known Activations