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

    Neuronpedia

    INDEX
    Explanations

    citation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    еть
    -0.06
     jobs
    -0.06
    oyo
    -0.06
    Boost
    -0.06
    armor
    -0.05
    _ke
    -0.05
     PREFIX
    -0.05
    Building
    -0.05
    Approved
    -0.05
     readings
    -0.05
    POSITIVE LOGITS
    xBF
    0.07
     schon
    0.07
    뿐
    0.07
     retarded
    0.07
    .last
    0.07
    -------
    0.07
    .§
    0.06
    spiel
    0.06
    	spec
    0.06
    /Edit
    0.06
    Act Density 0.008%

    No Known Activations