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

    Neuronpedia

    INDEX
    Explanations

    cell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     shape
    -0.27
     calculated
    -0.26
     velocity
    -0.26
    serter
    -0.25
    ãĤ¯ãĥĪ
    -0.25
     palate
    -0.25
    ä»ħä»ħæĺ¯
    -0.25
     present
    -0.24
    å¤©åºľ
    -0.24
     preserves
    -0.24
    POSITIVE LOGITS
    mal
    0.27
    åİŁåŃIJ
    0.26
     Rays
    0.26
    intros
    0.26
     Radi
    0.26
    WARDS
    0.25
     atom
    0.25
     Bless
    0.25
     regs
    0.24
    onna
    0.24
    Act Density 0.015%

    No Known Activations