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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ”—
    -0.07
    _gt
    -0.07
     iam
    -0.07
    >";
    -0.06
    ,’’
    -0.06
    _BUILD
    -0.06
     Cah
    -0.06
    (fun
    -0.06
     其他
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    };↵↵↵
    0.07
     CommonModule
    0.07
    ↵        
↵
    0.07
     towards
    0.07
     amongst
    0.07
    ()↵↵↵↵
    0.06
    DH
    0.06
     kì
    0.06
     amidst
    0.06
        
↵
    0.06
    Act Density 1.037%

    No Known Activations