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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    usions
    -0.07
     poměr
    -0.07
    villa
    -0.07
    Sigma
    -0.06
     б
    -0.06
     Μα
    -0.06
     Bell
    -0.06
     سبک
    -0.06
     crimson
    -0.06
     юрид
    -0.06
    POSITIVE LOGITS
    alloc
    0.07
     �
    0.07
    şam
    0.07
     enter
    0.07
     anzeigen
    0.07
     heartbreaking
    0.07
     really
    0.06
     oneself
    0.06
     who
    0.06
    Otherwise
    0.06
    Act Density 0.068%

    No Known Activations