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

    Neuronpedia

    INDEX
    Explanations

    added

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     correo
    -0.07
    desk
    -0.07
    quina
    -0.07
     costume
    -0.07
    	console
    -0.07
    景德
    -0.07
    excel
    -0.06
    Perl
    -0.06
     XK
    -0.06
    ambre
    -0.06
    POSITIVE LOGITS
     Marcos
    0.07
    charges
    0.07
    孟
    0.07
     благод
    0.07
    meg
    0.07
     Jonah
    0.07
     Gradient
    0.06
     tensions
    0.06
    的方法
    0.06
     pigs
    0.06
    Act Density 0.012%

    No Known Activations