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

    Neuronpedia

    INDEX
    Explanations

    npm package names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bestimmte
    0.43
     económico
    0.42
     verschiedene
    0.39
     coagulation
    0.39
     চৌধুরী
    0.39
     transfusion
    0.39
     penggunaan
    0.38
     typedef
    0.38
     Tuz
    0.38
    杼
    0.38
    POSITIVE LOGITS
     Bond
    0.39
    值得
    0.39
    Bond
    0.38
    ハイ
    0.36
     bond
    0.36
    Minecraft
    0.35
    ᓂ
    0.35
    bond
    0.35
    L
    0.35
    @
    0.35
    Act Density 0.000%

    No Known Activations