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

    Neuronpedia

    INDEX
    Explanations

    How things function/operate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "..\..\
    -0.60
     Ceramby
    -0.54
    Dichloroethene
    -0.53
    UserScript
    -0.51
     Nautilus
    -0.49
    kati
    -0.49
     Universitario
    -0.49
     Eros
    -0.48
     nether
    -0.48
     Yarm
    -0.47
    POSITIVE LOGITS
    <bos>
    1.04
    Geplaatst
    0.60
    OOTDTY
    0.56
    Gambas
    0.56
     يتيمه
    0.55
    солю
    0.55
    labus
    0.54
     once
    0.53
    Once
    0.53
     beginnetje
    0.52
    Act Density 0.020%

    No Known Activations