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

    Neuronpedia

    INDEX
    Explanations

    link

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تب
    -0.08
    aret
    -0.07
     tqdm
    -0.07
    >Login
    -0.07
     MEP
    -0.07
     materially
    -0.06
    .sec
    -0.06
    ihu
    -0.06
    лова
    -0.06
     hấp
    -0.06
    POSITIVE LOGITS
    	RTDBG
    0.06
     confronted
    0.06
     बर
    0.06
     ObjectType
    0.06
     shack
    0.06
    �
    0.05
    .days
    0.05
     ABOVE
    0.05
    .good
    0.05
    interpreted
    0.05
    Act Density 0.016%

    No Known Activations