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

    Neuronpedia

    INDEX
    Explanations

    technical explanations and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oporosis
    0.31
    audit
    0.29
    ,”
    0.29
    gard
    0.29
     మొద
    0.28
    oa
    0.27
    AIR
    0.27
    EMPL
    0.27
    aan
    0.27
    <h5>
    0.27
    POSITIVE LOGITS
     আলোচ
    0.26
    兮
    0.26
     mocker
    0.26
     striped
    0.25
     ще
    0.25
     sickly
    0.25
     souh
    0.24
    μοι
    0.24
     snowman
    0.24
    痛
    0.24
    Act Density 0.000%

    No Known Activations