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

    Neuronpedia

    INDEX
    Explanations

    wills

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Plan
    -0.07
    کر
    -0.07
    .Apply
    -0.06
    SAFE
    -0.06
     typings
    -0.06
     measured
    -0.06
    quila
    -0.06
     сто
    -0.06
     Placement
    -0.06
    _safe
    -0.06
    POSITIVE LOGITS
    opia
    0.07
     CString
    0.06
    τέλε
    0.06
     مك
    0.06
    mae
    0.06
    implemented
    0.06
     터
    0.06
     ASE
    0.06
     Highlander
    0.06
     reconstruct
    0.06
    Act Density 0.062%

    No Known Activations