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

    Neuronpedia

    INDEX
    Explanations

    Asking questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lda
    -0.08
    .K
    -0.07
     INT
    -0.07
    	K
    -0.07
     BIN
    -0.07
     k
    -0.07
    <input
    -0.07
     uk
    -0.06
    traditional
    -0.06
     gv
    -0.06
    POSITIVE LOGITS
    мець
    0.07
     predic
    0.07
     (--
    0.07
    ومی
    0.06
    ῶ
    0.06
     thọ
    0.06
     Mitgli
    0.06
    (doc
    0.06
     облі
    0.06
    (parts
    0.06
    Act Density 0.026%

    No Known Activations