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

    Neuronpedia

    INDEX
    Explanations

    quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
      
    -0.07
     двух
    -0.07
    ist
    -0.07
    VertexArray
    -0.06
    ANY
    -0.06
    any
    -0.06
    -0.06
    ?
    -0.06
     Palm
    -0.06
     jed
    -0.06
    POSITIVE LOGITS
    "I
    0.10
    “I
    0.09
    “The
    0.09
    "The
    0.09
    "You
    0.08
    “You
    0.08
    “We
    0.08
    _EFFECT
    0.08
    "We
    0.07
    “It
    0.07
    Act Density 0.025%

    No Known Activations