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

    Neuronpedia

    INDEX
    Explanations

    change over time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Cold
    -0.06
    .duration
    -0.06
     Nature
    -0.06
    rott
    -0.06
     massaggi
    -0.06
     Principal
    -0.06
     Mor
    -0.06
    paralleled
    -0.06
     singly
    -0.06
     Sp
    -0.05
    POSITIVE LOGITS
    trie
    0.07
    锋
    0.07
    -monitor
    0.07
     área
    0.07
    Ay
    0.06
     strengthen
    0.06
    -cent
    0.06
     Pom
    0.06
     قاب
    0.06
    ा-
    0.06
    Act Density 0.025%

    No Known Activations