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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ':'
    -0.07
     ponds
    -0.07
     bağlı
    -0.07
    �
    -0.07
    瘭
    -0.07
     רק
    -0.07
     Los
    -0.07
    .frequency
    -0.06
     Baltic
    -0.06
     accumulation
    -0.06
    POSITIVE LOGITS
    𝐯
    0.07
    ʨ
    0.07
    𝐟
    0.07
    ⾦
    0.06
    导
    0.06
     gouver
    0.06
     vw
    0.06
    	X
    0.06
    Coeff
    0.06
    	f
    0.06
    Act Density 0.084%

    No Known Activations