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

    Neuronpedia

    INDEX
    Explanations

    extensions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drift
    -0.08
     sanitizer
    -0.07
    ρο
    -0.07
    läufig
    -0.07
     curiosity
    -0.07
     координ
    -0.07
     matters
    -0.07
     చూస
    -0.07
    Editable
    -0.07
     mace
    -0.07
    POSITIVE LOGITS
     hairstyle
    0.10
     Technique
    0.09
     técnicas
    0.09
     hairstyles
    0.09
     techniques
    0.09
     Techniques
    0.09
     technique
    0.09
     Hairstyles
    0.09
     européen
    0.09
     etabli
    0.09
    Act Density 0.003%

    No Known Activations