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

    Neuronpedia

    INDEX
    Explanations

    acronyms/abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    한테
    -0.06
    ensity
    -0.06
    _ENC
    -0.06
     Vaults
    -0.06
    DATED
    -0.06
     Elizabeth
    -0.06
     NOT
    -0.06
    อท
    -0.06
     validar
    -0.06
     prescription
    -0.06
    POSITIVE LOGITS
     verbally
    0.07
     spre
    0.06
     algum
    0.06
    推
    0.06
    _due
    0.06
    ,$
    0.06
    _bl
    0.06
     todas
    0.06
    �
    0.06
     taj
    0.06
    Act Density 0.057%

    No Known Activations