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

    Neuronpedia

    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AJOR
    -0.06
     factual
    -0.06
    fleet
    -0.06
    istine
    -0.06
    istrov
    -0.06
    氏
    -0.06
     deleg
    -0.06
    리고
    -0.06
    라
    -0.06
     hasattr
    -0.06
    POSITIVE LOGITS
    -divider
    0.07
     Canadian
    0.07
     použí
    0.07
    erspective
    0.07
    .requires
    0.07
     perceive
    0.07
    California
    0.06
     haben
    0.06
     NI
    0.06
    .setStroke
    0.06
    Act Density 0.006%

    No Known Activations