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

    Neuronpedia

    INDEX
    Explanations

    well-formed English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    런
    -0.07
    icial
    -0.06
     �
    -0.06
    ollower
    -0.06
     Пар
    -0.06
    庄
    -0.06
    round
    -0.06
    Carl
    -0.06
     enorm
    -0.06
    kemiz
    -0.06
    POSITIVE LOGITS
    ený
    0.07
     training
    0.06
    meth
    0.06
     /^
    0.06
    .required
    0.06
     fully
    0.06
     Luca
    0.06
     holidays
    0.06
     обычно
    0.06
     witnesses
    0.06
    Act Density 0.000%

    No Known Activations