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

    Neuronpedia

    INDEX
    Explanations

    string

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sta
    -0.07
     Damen
    -0.07
     Reads
    -0.07
     kterou
    -0.07
    Width
    -0.06
    _Message
    -0.06
    Delete
    -0.06
    Backup
    -0.06
    -angle
    -0.06
     sweating
    -0.06
    POSITIVE LOGITS
     هر
    0.07
     polishing
    0.06
     enumerated
    0.06
     advancing
    0.06
     luckily
    0.06
    など
    0.06
     ########################
    0.06
    .extensions
    0.06
     �
    0.06
    	es
    0.06
    Act Density 0.007%

    No Known Activations