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

    Neuronpedia

    INDEX
    Explanations

    own

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mayo
    -0.08
    ']].
    -0.07
    gons
    -0.06
    edii
    -0.06
    ])]
    -0.06
     �
    -0.06
    cce
    -0.06
    اضر
    -0.06
    ulen
    -0.06
     ।
    -0.06
    POSITIVE LOGITS
    419
    0.07
     IMAGE
    0.07
    friends
    0.07
    exact
    0.07
    input
    0.06
    dictionary
    0.06
     Forum
    0.06
    immutable
    0.06
     friends
    0.06
    .replace
    0.06
    Act Density 0.000%

    No Known Activations