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

    Neuronpedia

    INDEX
    Explanations

    private, one-on-one, alone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াগ
    0.39
    omsday
    0.36
    ufs
    0.35
    很容易
    0.34
     placas
    0.34
     cape
    0.33
    限界
    0.32
     इम्मेडिएटली
    0.32
    ⠄
    0.32
     nitrates
    0.32
    POSITIVE LOGITS
     private
    1.46
    Private
    1.36
    一对
    1.34
    private
    1.33
    私
    1.32
     privately
    1.23
     privata
    1.22
     Private
    1.21
     निजी
    1.18
     приват
    1.17
    Act Density 0.043%

    No Known Activations