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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     implications
    -0.07
    icare
    -0.07
     Inter
    -0.06
    rido
    -0.06
    Living
    -0.06
     IL
    -0.06
     Iter
    -0.06
    аря
    -0.06
    iosis
    -0.06
     conce
    -0.06
    POSITIVE LOGITS
     Millions
    0.07
     detta
    0.06
    0.06
    /portfolio
    0.06
    /controllers
    0.06
    0.06
    loggedIn
    0.06
     assures
    0.06
    言った
    0.06
    _rw
    0.06
    Act Density 0.002%

    No Known Activations