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

    Neuronpedia

    INDEX
    Explanations

    invention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nath
    -0.07
     отмет
    -0.07
    _TYPEDEF
    -0.06
    ############################################################
    -0.06
     Denis
    -0.06
     стат
    -0.06
     Raqqa
    -0.06
     possibilit
    -0.06
     Charl
    -0.06
     sheets
    -0.06
    POSITIVE LOGITS
     imaginable
    0.06
    Ž
    0.06
    failure
    0.06
    รรม
    0.06
    .checked
    0.06
    背
    0.06
    orne
    0.06
    ."'
    0.06
     болезни
    0.06
     termination
    0.06
    Act Density 0.005%

    No Known Activations