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

    Neuronpedia

    INDEX
    Explanations

    and linking related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hills
    0.60
     disbelief
    0.57
     atoms
    0.57
     mountains
    0.57
     gums
    0.54
     etc
    0.52
     beliefs
    0.51
     swelling
    0.51
     you
    0.51
     substances
    0.50
    POSITIVE LOGITS
    /
    0.58
    Advanced
    0.56
    acular
    0.52
    ignal
    0.52
    Gateway
    0.49
    extrémité
    0.48
     második
    0.48
    Otherwise
    0.46
    ／
    0.46
    Proposed
    0.46
    Act Density 0.496%

    No Known Activations