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

    Neuronpedia

    INDEX
    Explanations

    English text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.08
    		↵		↵		↵
    -0.08
     vůbec
    -0.07
    collision
    -0.06
    lední
    -0.06
    Head
    -0.06
     rt
    -0.06
    裡
    -0.06
     fich
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     kostenlose
    0.06
     Considering
    0.06
     Recorded
    0.06
     gramm
    0.06
     Diff
    0.06
     poor
    0.06
     secure
    0.06
    hen
    0.06
     mev
    0.06
     absorbed
    0.06
    Act Density 0.000%

    No Known Activations