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

    Neuronpedia

    INDEX
    Explanations

    utf-8 encoding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OutgoingRiver
    0.32
    MyToolkit
    0.30
    lyPlugin
    0.29
    ukiyoe
    0.29
    صیٰ
    0.29
    Therates
    0.29
    <unused307>
    0.29
    Prothorax
    0.28
    TorpedoStore
    0.28
    ennzeichnet
    0.28
    POSITIVE LOGITS
    S
    0.37
    ↵
    0.37
    0.36
     S
    0.35
    ↵↵
    0.32
    5
    0.30
    2
    0.29
     F
    0.29
    R
    0.29
    s
    0.28
    Act Density 0.000%

    No Known Activations