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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     price
    -0.07
     traveling
    -0.07
    假如
    -0.07
    Ἡ
    -0.07
    옌
    -0.07
    LLLL
    -0.06
     gdy
    -0.06
    Installing
    -0.06
    ASCII
    -0.06
    	If
    -0.06
    POSITIVE LOGITS
     balanced
    0.07
    可信
    0.07
    -centric
    0.07
    も多い
    0.07
     opted
    0.07
    庥
    0.07
    .control
    0.06
     онл
    0.06
    積極
    0.06
     Alternate
    0.06
    Act Density 0.017%

    No Known Activations