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

    Neuronpedia

    INDEX
    Explanations

    months and seasons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تر
    0.85
     ark
    0.83
    மை
    0.83
     تهد
    0.83
     kuid
    0.82
     los
    0.81
    ڈر
    0.81
     ير
    0.80
     rendah
    0.80
     Allied
    0.80
    POSITIVE LOGITS
    iatura
    0.82
    Activities
    0.74
    thol
    0.67
     vignettes
    0.66
    kräft
    0.66
     Activities
    0.65
    akili
    0.64
     subclasses
    0.64
    0.64
    ="#!"
    0.64
    Act Density 0.147%

    No Known Activations