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

    Neuronpedia

    INDEX
    Explanations

    Code snippets or formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     problemas
    -0.07
    "/>
↵
    -0.06
    Arrow
    -0.06
    	mem
    -0.06
    .That
    -0.06
    Uploaded
    -0.06
    Cards
    -0.06
     Fecha
    -0.06
     cher
    -0.06
     рек
    -0.06
    POSITIVE LOGITS
    .multi
    0.07
     agree
    0.06
    	payload
    0.06
    traction
    0.06
    不同
    0.06
     shampoo
    0.06
     Pull
    0.06
    .off
    0.06
     �
    0.06
    coin
    0.06
    Act Density 0.001%

    No Known Activations