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

    Neuronpedia

    INDEX
    Explanations

    very

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .syntax
    -0.07
    ывать
    -0.07
     khẳng
    -0.07
    Tim
    -0.06
     toda
    -0.06
    secure
    -0.06
    .coord
    -0.06
     vyp
    -0.06
     yılda
    -0.06
    _Column
    -0.06
    POSITIVE LOGITS
     immediately
    0.07
     XT
    0.07
     plc
    0.07
     Definitely
    0.07
     Association
    0.06
     Mus
    0.06
     vv
    0.06
    RA
    0.06
     especially
    0.06
    _SYM
    0.06
    Act Density 0.009%

    No Known Activations