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
     settled
    -0.07
     maker
    -0.07
    .intro
    -0.07
     Ceremony
    -0.06
    Effects
    -0.06
     temple
    -0.06
     Carlos
    -0.06
     cares
    -0.06
    Adds
    -0.06
     unicorn
    -0.06
    POSITIVE LOGITS
    ī
    0.06
     Richards
    0.06
    CategoryId
    0.06
     jsonObject
    0.06
    톡
    0.06
    ，又
    0.06
    virtual
    0.06
    hf
    0.06
    ;(
    0.06
    ード
    0.05
    Act Density 0.001%

    No Known Activations