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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _readable
    -0.06
    multiply
    -0.06
    ableViewController
    -0.06
     Mig
    -0.06
     مورد
    -0.06
     momentarily
    -0.06
    ์พ
    -0.06
     mourning
    -0.06
     Однак
    -0.06
    ylvania
    -0.06
    POSITIVE LOGITS
     tanker
    0.07
     objective
    0.07
     load
    0.07
     objectives
    0.07
     LOAD
    0.07
    \base
    0.07
     java
    0.07
     Funding
    0.07
     leased
    0.07
    refer
    0.06
    Act Density 0.029%

    No Known Activations