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

    Neuronpedia

    INDEX
    Explanations

    Newlines and quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     بول
    -0.07
    -hard
    -0.07
     derin
    -0.06
     στρα
    -0.06
    allenge
    -0.06
     dando
    -0.06
     kterých
    -0.06
     눈
    -0.06
     twelve
    -0.06
    _lex
    -0.06
    POSITIVE LOGITS
    修
    0.07
     firm
    0.06
    _remove
    0.06
     Suitable
    0.06
    >B
    0.06
     orchestrated
    0.06
     Valor
    0.06
     Gener
    0.06
     Essays
    0.06
     Visible
    0.06
    Act Density 0.030%

    No Known Activations