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

    Neuronpedia

    INDEX
    Explanations

    brackets/parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hijo
    -0.07
    newline
    -0.07
     nữ
    -0.07
    шие
    -0.07
    Fear
    -0.06
    Cont
    -0.06
     inactive
    -0.06
    	void
    -0.06
     payloads
    -0.06
     uploaded
    -0.06
    POSITIVE LOGITS
    .opt
    0.07
    　　 　 　 　 　
    0.07
    ≤
    0.06
     сот
    0.06
     大阪
    0.06
     elapsedTime
    0.06
     Jackets
    0.06
     Terraria
    0.06
     αντι
    0.06
     adversely
    0.06
    Act Density 0.008%

    No Known Activations