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

    Neuronpedia

    INDEX
    Explanations

    's

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ,arg
    -0.08
    reta
    -0.07
    (inode
    -0.07
     Ağustos
    -0.07
    _BIND
    -0.07
    에너
    -0.07
     attributes
    -0.07
    .GridColumn
    -0.07
     begr
    -0.07
    unifu
    -0.07
    POSITIVE LOGITS
     Essentially
    0.08
    Basically
    0.07
    澄
    0.07
     director
    0.07
    ח
    0.07
     delim
    0.07
    Increases
    0.07
    陰
    0.06
    𝖓
    0.06
     Sch
    0.06
    Act Density 0.001%

    No Known Activations