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

    Neuronpedia

    INDEX
    Explanations

    license type specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ulation
    3.41
    ü
    2.46
    ू
    2.43
    hasil
    2.43
    nue
    2.42
    ъем
    2.41
    𝓊
    2.39
    nu
    2.28
     Bayes
    2.27
    veis
    2.26
    POSITIVE LOGITS
    ภัย
    3.18
    वें
    2.94
    embra
    2.88
    علم
    2.87
     Inference
    2.87
    ायत
    2.80
     premises
    2.77
    ek
    2.76
    فة
    2.71
    hood
    2.69
    Act Density 0.011%

    No Known Activations