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

    Neuronpedia

    INDEX
    Explanations

    thinkers and their "-ian" descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Its
    0.43
    ds
    0.40
     its
    0.39
    riert
    0.39
    rils
    0.38
    awesome
    0.37
    rient
    0.37
    powerful
    0.36
     danske
    0.36
    reetings
    0.36
    POSITIVE LOGITS
     himself
    0.99
    ian
    0.94
    esque
    0.80
    ianas
    0.75
    IAN
    0.70
    iana
    0.68
     Himself
    0.67
    vian
    0.63
    ियन
    0.63
    ians
    0.62
    Act Density 0.016%

    No Known Activations