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

    Neuronpedia

    INDEX
    Explanations

    pole/post

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     desconoc
    -0.08
     unauthorized
    -0.08
     hem
    -0.08
    Salt
    -0.07
     Tome
    -0.07
     obe
    -0.07
    Hem
    -0.07
     बी
    -0.07
    =password
    -0.07
     tired
    -0.07
    POSITIVE LOGITS
     Located
    0.09
     happening
    0.09
    附近
    0.09
     situé
    0.08
     breakthroughs
    0.08
     located
    0.08
     순간
    0.08
     situated
    0.08
     située
    0.08
     praktisch
    0.08
    Act Density 0.009%

    No Known Activations