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

    Neuronpedia

    INDEX
    Explanations

    historic school

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    莫
    0.43
     Logo
    0.42
    ází
    0.41
    绕
    0.40
     Biodiversity
    0.40
     Potential
    0.40
     Concert
    0.40
     Threat
    0.39
     Furious
    0.39
    耔
    0.39
    POSITIVE LOGITS
     propia
    0.40
     cheery
    0.39
     camera
    0.38
     자신의
    0.38
    camera
    0.38
    sher
    0.37
     stance
    0.37
     homegrown
    0.37
     cheerful
    0.36
     unassuming
    0.36
    Act Density 0.001%

    No Known Activations