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

    Neuronpedia

    INDEX
    Explanations

    own

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Test
    -0.07
    _prices
    -0.07
     �
    -0.07
     consisting
    -0.06
    erable
    -0.06
    lamaya
    -0.06
     Solution
    -0.06
     specialist
    -0.06
    charger
    -0.06
    _parallel
    -0.06
    POSITIVE LOGITS
     Blocked
    0.06
     Pond
    0.06
    URAL
    0.06
    ือง
    0.06
    ptune
    0.06
    _marks
    0.06
     клад
    0.06
     certainty
    0.06
    	org
    0.06
    >${
    0.06
    Act Density 0.013%

    No Known Activations