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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FF
    -0.07
     pairing
    -0.06
     Negative
    -0.06
    	core
    -0.06
     Fischer
    -0.06
     granny
    -0.06
     probing
    -0.06
     Reflex
    -0.06
     平
    -0.06
     usado
    -0.06
    POSITIVE LOGITS
    sume
    0.06
    ?“↵↵
    0.06
    ?q
    0.06
    _pas
    0.06
     subclass
    0.06
    }`;↵
    0.06
    phan
    0.06
    rega
    0.06
    POOL
    0.06
     %↵↵
    0.05
    Act Density 0.001%

    No Known Activations