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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Axes
    -0.07
     loops
    -0.07
     LO
    -0.07
    owed
    -0.06
    ;d
    -0.06
     aantal
    -0.06
     gente
    -0.06
     banc
    -0.06
    ange
    -0.06
    too
    -0.06
    POSITIVE LOGITS
    .getOwnProperty
    0.07
    .Object
    0.06
    .Camera
    0.06
    _ARG
    0.06
    arrival
    0.06
     Slam
    0.06
     journée
    0.06
    Listen
    0.06
     τελευτα
    0.06
    -selling
    0.06
    Act Density 0.019%

    No Known Activations