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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     indoors
    -0.07
    เฟ
    -0.07
     studi
    -0.07
    spiel
    -0.07
    _hash
    -0.07
    _TOOL
    -0.07
    illation
    -0.07
    alo
    -0.07
    Su
    -0.07
    aturdays
    -0.07
    POSITIVE LOGITS
     النه
    0.06
    纸
    0.06
     Scalia
    0.06
     Rencontre
    0.06
     основі
    0.06
     Jonah
    0.06
     попада
    0.06
    _rsp
    0.06
     ΠΡ
    0.05
    (Profile
    0.05
    Act Density 0.028%

    No Known Activations