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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prompting
    -0.07
    .tag
    -0.07
    _pol
    -0.06
    ùng
    -0.06
    Numeric
    -0.06
    _ordered
    -0.06
    expects
    -0.06
    ……
    -0.06
     directive
    -0.06
     боль
    -0.06
    POSITIVE LOGITS
     kavram
    0.07
     flowers
    0.06
    emplate
    0.06
    LOAT
    0.06
     мак
    0.06
    cae
    0.06
     khỏi
    0.06
    _title
    0.06
    �
    0.06
    nilai
    0.06
    Act Density 0.023%

    No Known Activations