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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ASM
    -0.06
     neurotrans
    -0.06
     empty
    -0.06
     Param
    -0.06
     Chill
    -0.06
    学院
    -0.06
    nost
    -0.06
     Controllers
    -0.06
    Tu
    -0.06
    ublish
    -0.06
    POSITIVE LOGITS
    áme
    0.07
    "log
    0.07
    horn
    0.07
     dns
    0.07
    ıb
    0.06
    ピー
    0.06
    イン
    0.06
     нее
    0.06
    कन
    0.06
    ンバー
    0.06
    Act Density 0.012%

    No Known Activations