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

    Neuronpedia

    INDEX
    Explanations

    math sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rede
    -0.07
    (material
    -0.07
     scare
    -0.07
    BOVE
    -0.07
    poss
    -0.07
     horrors
    -0.07
     Redirect
    -0.06
     playa
    -0.06
     reassure
    -0.06
    handle
    -0.06
    POSITIVE LOGITS
    чної
    0.06
    �
    0.06
     복
    0.06
    antics
    0.06
    如此
    0.06
     TimeUnit
    0.06
    -web
    0.06
    оло
    0.06
    EndTime
    0.06
     обязательно
    0.05
    Act Density 0.005%

    No Known Activations