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

    Neuronpedia

    INDEX
    Explanations

    .php?term=

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     przechowy
    0.48
    其他的
    0.44
    verständ
    0.43
    दूसरे
    0.41
     ۾
    0.40
     hippocampal
    0.39
     zusätzlichen
    0.38
     dalších
    0.38
     chronograph
    0.38
    亠
    0.38
    POSITIVE LOGITS
    name
    0.52
     action
    0.50
    infile
    0.49
    filename
    0.48
     filename
    0.47
    lname
    0.46
    id
    0.46
     id
    0.45
    path
    0.45
     name
    0.45
    Act Density 0.007%

    No Known Activations