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

    Neuronpedia

    INDEX
    Explanations

    Scientific/medical research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.06
     повед
    -0.06
     FindObjectOfType
    -0.06
    _FW
    -0.06
     thông
    -0.06
    ransition
    -0.06
    dropIfExists
    -0.06
     其
    -0.06
    _idxs
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     Ac
    0.07
     steel
    0.07
    steel
    0.07
     Roh
    0.07
    .hidden
    0.07
     Goose
    0.07
     overlooked
    0.07
     Exclude
    0.07
     deliberate
    0.06
    /Documents
    0.06
    Act Density 0.484%

    No Known Activations