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

    Neuronpedia

    INDEX
    Explanations

    code annotations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eus
    -0.07
    _AUT
    -0.07
    าณ
    -0.07
     attn
    -0.06
     꽃
    -0.06
    .spotify
    -0.06
    threat
    -0.06
    狀
    -0.06
    they
    -0.06
    ürger
    -0.06
    POSITIVE LOGITS
    -owner
    0.06
    patial
    0.06
     inning
    0.06
    ])(
    0.06
     dwelling
    0.06
    	assert
    0.06
     surveyed
    0.06
     hlavní
    0.06
     overclock
    0.06
     crafted
    0.06
    Act Density 0.011%

    No Known Activations