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

    Neuronpedia

    INDEX
    Explanations

    citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     naam
    -0.08
    "d
    -0.06
    ooo
    -0.06
    "=>
    -0.06
    unci
    -0.06
    mind
    -0.06
    question
    -0.06
    ACHER
    -0.06
     }↵↵↵↵↵↵
    -0.06
    .ReadAllText
    -0.06
    POSITIVE LOGITS
    やる夫
    0.07
    	arr
    0.06
     Restoration
    0.06
    ็ตาม
    0.06
     更新
    0.06
    拥有
    0.06
     abs
    0.06
            
↵
↵
    0.06
     evade
    0.06
     lengths
    0.06
    Act Density 0.022%

    No Known Activations