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

    Neuronpedia

    INDEX
    Explanations

    links and resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defeats
    0.42
    Vincent
    0.41
     defeat
    0.41
    战
    0.40
    вос
    0.40
     surely
    0.39
     POST
    0.38
    肯定是
    0.38
    Sure
    0.38
    पोस्ट
    0.37
    POSITIVE LOGITS
     CNS
    0.62
    CNS
    0.57
     Ceremon
    0.46
     SND
    0.41
     IRS
    0.39
     अट
    0.39
    舧
    0.39
     seizure
    0.38
     EIR
    0.37
     seizing
    0.37
    Act Density 0.001%

    No Known Activations