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

    Neuronpedia

    INDEX
    Explanations

    mut

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (face
    -0.07
    "indices
    -0.06
     şeh
    -0.06
     CWE
    -0.06
    ้าย
    -0.06
    ğe
    -0.06
     ○
    -0.06
     IPA
    -0.06
     næ
    -0.06
     Ivy
    -0.06
    POSITIVE LOGITS
     developing
    0.07
    String
    0.07
     cultures
    0.07
    Closing
    0.07
     metabolism
    0.07
     trusting
    0.07
    Ens
    0.07
    _GUI
    0.06
    blog
    0.06
     nomin
    0.06
    Act Density 0.001%

    No Known Activations