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

    Neuronpedia

    INDEX
    Explanations

    Programming symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    乡
    -0.07
    evt
    -0.06
     �
    -0.06
     Force
    -0.06
     Раз
    -0.06
     cabin
    -0.06
    …↵↵↵↵
    -0.06
    	x
    -0.06
     qq
    -0.05
    "Yes
    -0.05
    POSITIVE LOGITS
    .digital
    0.07
    โซ
    0.07
    .Redis
    0.07
     этому
    0.07
     OF
    0.06
     od
    0.06
    بل
    0.06
     of
    0.06
    kus
    0.06
     niet
    0.06
    Act Density 0.013%

    No Known Activations