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

    Neuronpedia

    INDEX
    Explanations

    Scalp or Scala

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Strand
    -0.30
    hare
    -0.29
    诰
    -0.27
    AILS
    -0.26
    iat
    -0.26
    ead
    -0.26
    hips
    -0.26
     useClass
    -0.26
    å¿ĥåĬ¨
    -0.25
    缨
    -0.25
    POSITIVE LOGITS
    izar
    0.31
    ãģĹãģķ
    0.28
    ular
    0.25
    éĸī
    0.24
    éĵĿ
    0.24
    olo
    0.24
    .conn
    0.24
     roller
    0.24
     even
    0.24
    select
    0.24
    Act Density 0.051%

    No Known Activations