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

    Neuronpedia

    INDEX
    Explanations

    java code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pod
    -0.07
     Hav
    -0.06
     Müdür
    -0.06
     explosive
    -0.06
     Provider
    -0.06
     プ
    -0.06
     scrolling
    -0.06
     quý
    -0.06
    继
    -0.06
    젝트
    -0.06
    POSITIVE LOGITS
     Witt
    0.06
    emploi
    0.06
    archives
    0.06
    รว
    0.06
     Danielle
    0.06
    coli
    0.06
    �
    0.06
    ум
    0.06
     bem
    0.06
     предостав
    0.06
    Act Density 0.000%

    No Known Activations