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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﯛ
    -0.08
     По
    -0.07
     sudah
    -0.07
    	ZEPHIR
    -0.07
    羊
    -0.07
    .Pin
    -0.07
    面对面
    -0.07
     Canonical
    -0.07
     propensity
    -0.07
     Indy
    -0.06
    POSITIVE LOGITS
    ＃
    0.07
    rish
    0.07
    𝑹
    0.07
    ◉
    0.06
    _rights
    0.06
     como
    0.06
    荬
    0.06
     rewriting
    0.06
     uninterrupted
    0.06
    耻
    0.06
    Act Density 0.000%

    No Known Activations