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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ourage
    -0.06
    Called
    -0.06
     stakes
    -0.06
     Common
    -0.06
    ixa
    -0.06
     Nodes
    -0.06
     Poetry
    -0.06
     Validates
    -0.06
     stout
    -0.06
    Validators
    -0.06
    POSITIVE LOGITS
    -appointed
    0.07
    .VK
    0.07
    OPY
    0.06
    :bg
    0.06
    ──
    0.06
    nummer
    0.06
     güzel
    0.06
                                                                    
    0.06
     xu
    0.06
     सरक
    0.06
    Act Density 0.023%

    No Known Activations