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

    Neuronpedia

    INDEX
    Explanations

    tb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _movie
    -0.07
    046
    -0.07
     disappearance
    -0.07
     does
    -0.07
     bamb
    -0.07
     firmy
    -0.06
    stdbool
    -0.06
     showing
    -0.06
    において
    -0.06
     hier
    -0.06
    POSITIVE LOGITS
    Atom
    0.07
     Natalie
    0.07
    TEL
    0.07
    etak
    0.07
    tc
    0.07
    _tip
    0.07
    Italian
    0.07
    cg
    0.07
    etter
    0.07
    ichten
    0.07
    Act Density 0.336%

    No Known Activations