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

    Neuronpedia

    INDEX
    Explanations

    hard or soft states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    担心
    0.84
     Fear
    0.82
    <unused2116>
    0.81
    危機
    0.78
    恐惧
    0.77
    ▢
    0.77
    Fear
    0.77
    ᵐ
    0.77
     Spill
    0.76
    擔心
    0.76
    POSITIVE LOGITS
    eners
    0.79
    wired
    0.77
    core
    0.75
    ified
    0.74
     hearted
    0.74
    reset
    0.71
     आलो
    0.70
    wares
    0.69
     hitting
    0.68
    coded
    0.68
    Act Density 0.217%

    No Known Activations