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

    Neuronpedia

    INDEX
    Explanations

    durable

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     practicing
    -0.07
     certificate
    -0.07
     view
    -0.07
    Preview
    -0.07
     provisioning
    -0.07
     sideways
    -0.07
     spos
    -0.06
     sco
    -0.06
    phins
    -0.06
     incident
    -0.06
    POSITIVE LOGITS
    普
    0.08
    朱
    0.08
    %%*/
    0.07
    耐
    0.07
     sperm
    0.07
     Dur
    0.07
     政
    0.07
    久久
    0.07
    物理
    0.07
     '/')↵
    0.07
    Act Density 0.003%

    No Known Activations