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

    Neuronpedia

    INDEX
    Explanations

    descriptive negative situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ing
    0.39
    𝐧
    0.38
    allen
    0.37
    ellingen
    0.37
    ليس
    0.37
    ⵍ
    0.36
    Cheng
    0.36
    Sim
    0.35
     ਉ
    0.35
    𝐄
    0.35
    POSITIVE LOGITS
     polystyrene
    0.43
     tangle
    0.39
     puddle
    0.39
    סה
    0.38
     sergeant
    0.38
     sgt
    0.38
     optimum
    0.38
     agony
    0.38
     rained
    0.37
     terminou
    0.37
    Act Density 0.001%

    No Known Activations