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

    Neuronpedia

    INDEX
    Explanations

    Opinions and suggestions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yanı
    -0.07
     difficulties
    -0.07
    BF
    -0.07
     wolves
    -0.07
    跋
    -0.07
    атель
    -0.07
    ᵀ
    -0.07
    ologists
    -0.06
    预料
    -0.06
     manifold
    -0.06
    POSITIVE LOGITS
    		
↵		
↵
    0.08
     '''
↵
    0.07
     See
    0.06
    ﯭ
    0.06
     educated
    0.06
    __*/
    0.06
    Allocate
    0.06
     RIGHT
    0.06
    ⚥
    0.06
    mind
    0.06
    Act Density 0.102%

    No Known Activations