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

    Neuronpedia

    INDEX
    Explanations

    local services

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _integer
    -0.07
    gne
    -0.07
    ustering
    -0.06
    rov
    -0.06
    oute
    -0.06
    aaaa
    -0.06
    dge
    -0.06
    oksen
    -0.06
    .send
    -0.06
     davidjl
    -0.06
    POSITIVE LOGITS
    	Context
    0.07
    .snp
    0.06
    mi
    0.06
     СРСР
    0.06
    .Design
    0.06
     Slater
    0.06
     بالإ
    0.06
    الأ
    0.06
    Disney
    0.06
    _MARKER
    0.06
    Act Density 0.023%

    No Known Activations