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

    Neuronpedia

    INDEX
    Explanations

    /html

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Alright
    -0.07
    自治
    -0.06
    .readAs
    -0.06
    proper
    -0.06
     geschichten
    -0.06
     mar
    -0.06
     jedem
    -0.06
    ौन
    -0.06
     JB
    -0.06
     kâ
    -0.06
    POSITIVE LOGITS
    universal
    0.07
    /html
    0.07
     Apple
    0.07
     Fresh
    0.06
    Apple
    0.06
     specializing
    0.06
    นน
    0.06
    ILITY
    0.06
    �
    0.06
    holes
    0.06
    Act Density 0.001%

    No Known Activations