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

    Neuronpedia

    INDEX
    Explanations

    profile

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    568
    -0.07
    874
    -0.07
    _TEST
    -0.07
    052
    -0.07
    570
    -0.06
    571
    -0.06
     insect
    -0.06
    	task
    -0.06
     Easter
    -0.06
    ({'
    -0.06
    POSITIVE LOGITS
     profile
    0.11
     profiles
    0.11
    "profile
    0.09
     Profile
    0.09
    規
    0.08
    Л
    0.08
    Profiles
    0.08
     PROFILE
    0.08
    _PROFILE
    0.07
    ☴
    0.07
    Act Density 0.012%

    No Known Activations