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

    Neuronpedia

    INDEX
    Explanations

    UI elements after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hunting
    0.72
     Hlav
    0.71
     Barbie
    0.68
     Rodr
    0.66
     Hunter
    0.66
     stricken
    0.66
     Anastasia
    0.65
     Monst
    0.65
     Housing
    0.65
     Montana
    0.65
    POSITIVE LOGITS
    но
    0.77
    型の
    0.75
    де
    0.75
    די
    0.72
    cana
    0.71
    γν
    0.71
    си
    0.70
    со
    0.68
    ци
    0.68
    ্ড
    0.67
    Act Density 0.000%

    No Known Activations