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

    Neuronpedia

    INDEX
    Explanations

    `how` parameter values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     किलो
    0.60
     cysts
    0.60
     Cytol
    0.59
     filhos
    0.58
    ophthal
    0.57
     vesicles
    0.57
     assassins
    0.57
     orchids
    0.56
     canisters
    0.56
     algae
    0.55
    POSITIVE LOGITS
    Format
    0.55
    ՝
    0.54
    ́
    0.51
    </sup>
    0.50
    Earlier
    0.50
    ),
    0.49
    Existence
    0.49
    Based
    0.48
    ̀
    0.48
    ̈
    0.48
    Act Density 0.000%

    No Known Activations