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

    Neuronpedia

    INDEX
    Explanations

    class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Range
    -0.06
    logo
    -0.06
    pas
    -0.06
     Letter
    -0.06
    (Sender
    -0.06
    logradouro
    -0.06
    (Level
    -0.06
    _soft
    -0.06
    Member
    -0.06
     lö
    -0.06
    POSITIVE LOGITS
    _UNDER
    0.07
     Kat
    0.06
     sched
    0.06
     styling
    0.06
     columna
    0.06
    	out
    0.06
     happiness
    0.06
     different
    0.06
     (;;)
    0.06
    cular
    0.06
    Act Density 0.001%

    No Known Activations