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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'A
    -0.06
     EITHER
    -0.06
    ォ
    -0.06
     области
    -0.06
     times
    -0.06
     hObject
    -0.05
     бук
    -0.05
     Волод
    -0.05
    _TRIGGER
    -0.05
     روند
    -0.05
    POSITIVE LOGITS
    険
    0.07
     thesis
    0.07
    (Error
    0.07
     tidy
    0.07
     dragon
    0.06
    afka
    0.06
     κ
    0.06
     Гар
    0.06
     �
    0.06
    argest
    0.06
    Act Density 0.000%

    No Known Activations