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
     helped
    -0.06
    PathVariable
    -0.06
    made
    -0.06
    spam
    -0.06
    _an
    -0.06
    )))↵↵↵
    -0.06
     kısa
    -0.06
     Step
    -0.06
     thanks
    -0.06
    	points
    -0.06
    POSITIVE LOGITS
    �
    0.08
    βολή
    0.06
    ้าส
    0.06
     endowed
    0.06
    .setAuto
    0.06
     McCl
    0.06
    _SCL
    0.06
    Formats
    0.06
    _pemb
    0.06
     mensagem
    0.06
    Act Density 0.039%

    No Known Activations