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

    Neuronpedia

    INDEX
    Explanations

    we are going

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ২
    -1.20
    Scott
    -1.17
    Didn
    -1.17
    Doesn
    -1.09
    Matt
    -1.09
    ১
    -1.08
     Menteri
    -1.07
    Referències
    -1.06
     więks
    -1.06
     står
    -1.05
    POSITIVE LOGITS
     very
    1.35
     Normally
    1.16
     strong
    1.11
     totally
    1.04
     cooperation
    1.03
     проє
    1.03
     different
    1.02
    uVar
    1.02
     maybe
    1.00
     huge
    1.00
    Act Density 0.079%

    No Known Activations