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

    Neuronpedia

    INDEX
    Explanations

    mixed topics, technical snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MAS
    -0.07
     BJ
    -0.07
     researchers
    -0.07
    PS
    -0.07
     Strength
    -0.07
     �
    -0.06
     sentence
    -0.06
     momentos
    -0.06
     Legendary
    -0.06
     торгів
    -0.06
    POSITIVE LOGITS
     anatomy
    0.07
    erin
    0.06
    acular
    0.06
    Valid
    0.06
     glance
    0.06
    642
    0.06
    eckého
    0.06
     harassment
    0.06
     TimeUnit
    0.06
    839
    0.06
    Act Density 0.000%

    No Known Activations