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

    Neuronpedia

    INDEX
    Explanations

    against

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -rock
    -0.28
    arness
    -0.27
     cost
    -0.27
    å¸ĤåľºéľĢæ±Ĥ
    -0.26
    è£ħ
    -0.25
    Enter
    -0.24
    Pack
    -0.24
    /plain
    -0.24
    pack
    -0.24
    though
    -0.23
    POSITIVE LOGITS
    人æĿĥ
    0.30
     hsv
    0.27
    æľīä¿¡å¿ĥ
    0.26
    æľ
    0.26
    çĶ·
    0.26
    INY
    0.26
    itioner
    0.25
     japanese
    0.25
     memories
    0.24
    PARATOR
    0.24
    Act Density 0.004%

    No Known Activations