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

    Neuronpedia

    INDEX
    Explanations

    code blocks and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hydride
    0.40
     InputListener
    0.39
     evoked
    0.39
     vudd
    0.38
     hydraz
    0.38
     amph
    0.38
     धरा
    0.37
    ⱱ
    0.37
    𐰰
    0.37
     heathen
    0.37
    POSITIVE LOGITS
     partner
    0.44
    partner
    0.41
    partners
    0.41
    special
    0.39
    home
    0.38
    iedz
    0.38
    Smile
    0.38
    rcParams
    0.38
    Galer
    0.37
    Forg
    0.37
    Act Density 0.000%

    No Known Activations