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

    Neuronpedia

    INDEX
    Explanations

    news media

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    мах
    -0.08
    ��
    -0.07
     deposition
    -0.07
     ELF
    -0.07
    operand
    -0.06
    _pos
    -0.06
     LOCK
    -0.06
    вания
    -0.06
     fraud
    -0.06
    ями
    -0.06
    POSITIVE LOGITS
     vanish
    0.07
     Bounty
    0.06
    olas
    0.06
     Instantiate
    0.06
    .DateField
    0.06
     moo
    0.06
     möchten
    0.06
    .EntityManager
    0.06
    _FMT
    0.06
    ltre
    0.06
    Act Density 0.035%

    No Known Activations