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

    Neuronpedia

    INDEX
    Explanations

    appointment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ModuleName
    -0.07
    下半
    -0.07
    parer
    -0.07
    _present
    -0.07
    ète
    -0.07
    stration
    -0.06
    yz
    -0.06
    Background
    -0.06
    -town
    -0.06
    者は
    -0.06
    POSITIVE LOGITS
     telefone
    0.07
    ~
    0.07
    0.07
     וכ
    0.06
     machines
    0.06
     Appointment
    0.06
     bom
    0.06
    פקיד
    0.06
     LIKE
    0.06
    翘
    0.06
    Act Density 0.005%

    No Known Activations