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

    Neuronpedia

    INDEX
    Explanations

    scores and temperatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lag
    0.38
    difference
    0.37
    save
    0.36
    ceeded
    0.36
    dropped
    0.36
    drop
    0.32
    getting
    0.32
    followed
    0.32
    with
    0.32
    fif
    0.32
    POSITIVE LOGITS
    zków
    0.38
     Laboratories
    0.38
     provocative
    0.34
     ऑर्गे
    0.33
     politischen
    0.33
     zullen
    0.33
    Laboratory
    0.33
     Geos
    0.33
     honey
    0.32
     Licensed
    0.32
    Act Density 0.003%

    No Known Activations