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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     것을
    -0.08
    reten
    -0.07
    dw
    -0.06
     polit
    -0.06
    .JsonIgnore
    -0.06
     newUser
    -0.06
     öğret
    -0.06
    ivol
    -0.06
     blockbuster
    -0.06
    ीमत
    -0.06
    POSITIVE LOGITS
    ock
    0.07
     ring
    0.07
    마사지
    0.06
     SPR
    0.06
     cannabis
    0.06
     MUCH
    0.06
     HASH
    0.06
    _WITH
    0.06
     کنم
    0.06
    렌
    0.06
    Act Density 0.024%

    No Known Activations