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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lesbians
    -0.08
     phát
    -0.07
     METH
    -0.07
     wget
    -0.07
     RGB
    -0.06
    Italic
    -0.06
    γέν
    -0.06
     nécess
    -0.06
     �
    -0.06
     yere
    -0.06
    POSITIVE LOGITS
    PLIC
    0.07
    Expr
    0.07
    cone
    0.06
     TE
    0.06
     Psalm
    0.06
    _TIMES
    0.06
    _ENTRY
    0.06
     cared
    0.06
     departamento
    0.06
    alley
    0.06
    Act Density 0.006%

    No Known Activations