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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    “Well
    -0.07
     بح
    -0.07
    "Well
    -0.07
    _DAY
    -0.06
    “My
    -0.06
    iteDatabase
    -0.06
    Blockly
    -0.06
     verileri
    -0.06
    OTES
    -0.06
     Nhĩ
    -0.06
    POSITIVE LOGITS
    แผน
    0.07
     actualizar
    0.07
    Credential
    0.06
     ss
    0.06
    .switch
    0.06
    umbed
    0.06
    elic
    0.06
    전히
    0.06
     значение
    0.06
    sim
    0.06
    Act Density 0.018%

    No Known Activations