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

    Neuronpedia

    INDEX
    Explanations

    birth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fair
    -0.07
    تمر
    -0.07
    _CLOCK
    -0.07
    _free
    -0.07
     fair
    -0.06
    ambre
    -0.06
    _yield
    -0.06
     kolo
    -0.06
    .getChannel
    -0.06
    _mgmt
    -0.06
    POSITIVE LOGITS
     Beth
    0.07
    宝
    0.06
    RIGHT
    0.06
    __,↵
    0.06
    цер
    0.06
    术
    0.06
    unbind
    0.06
     exhibiting
    0.06
    cipher
    0.06
     mum
    0.06
    Act Density 0.001%

    No Known Activations