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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     symptom
    -0.07
    ฑ
    -0.07
    ম
    -0.07
     theoretical
    -0.07
    を使
    -0.07
     одно
    -0.06
    utas
    -0.06
     speak
    -0.06
    >[↵
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    reachable
    0.08
    热烈
    0.07
    .tsv
    0.07
     coop
    0.07
     Lob
    0.07
     Crawford
    0.07
    _resolver
    0.06
     sedan
    0.06
     кажется
    0.06
     tablesp
    0.06
    Act Density 0.031%

    No Known Activations