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
     revital
    -0.07
     diminish
    -0.07
     �
    -0.07
    ndo
    -0.06
    Great
    -0.06
    ruba
    -0.06
    great
    -0.06
    ller
    -0.06
     ومع
    -0.06
     GREAT
    -0.06
    POSITIVE LOGITS
     humour
    0.06
    KeyName
    0.06
    itors
    0.06
    chars
    0.06
     owners
    0.06
     Relations
    0.06
     obě
    0.06
    	Delete
    0.06
    .program
    0.06
    �
    0.06
    Act Density 0.008%

    No Known Activations