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

    Neuronpedia

    INDEX
    Explanations

    aims objectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     theaters
    -0.06
     pře
    -0.06
    ombre
    -0.06
    .isNullOrEmpty
    -0.06
    andal
    -0.06
    �
    -0.06
     clown
    -0.06
    }}</
    -0.06
     shampoo
    -0.06
    有人
    -0.05
    POSITIVE LOGITS
     goals
    0.09
     objectives
    0.08
    (CharSequence
    0.07
    Goals
    0.07
     scoring
    0.07
     purpose
    0.07
     goal
    0.07
    _THE
    0.07
    中國
    0.07
     Collaboration
    0.07
    Act Density 0.053%

    No Known Activations